Predictive , Preventive And Personalized Medicine Research Articles

Artificial intelligence to improve ischemia prediction in Rubidium Positron Emission Tomography—a validation study

BackgroundPatients are referred to functional coronary artery disease (CAD) testing based on their pre-test probability (PTP) to search for myocardial ischemia. The recommended prediction tools incorporate three variables (symptoms, age, sex) and are easy to use, but have a limited diagnostic accuracy. Hence, a substantial proportion of non-invasive functional tests reveal no myocardial ischemia, leading to unnecessary radiation exposure and costs. Therefore, preselection of patients before ischemia testing needs to be improved using a more predictive and personalised approach.AimsUsing multiple variables (symptoms, vitals, ECG, biomarkers), artificial intelligence–based tools can provide a detailed and individualised profile of each patient. This could improve PTP assessment and provide a more personalised diagnostic approach in the framework of predictive, preventive and personalised medicine (PPPM).MethodsConsecutive patients (n = 2417) referred for Rubidium-82 positron emission tomography were evaluated. PTP was calculated using the ESC 2013/2019 and ACC 2012/2021 guidelines, and a memetic pattern–based algorithm (MPA) was applied incorporating symptoms, vitals, ECG and biomarkers. Five PTP categories from very low to very high PTP were defined (i.e., < 5%, 5–15%, 15–50%, 50–85%, > 85%). Ischemia was defined as summed difference score (SDS) ≥ 2.ResultsIschemia was present in 37.1%. The MPA model was most accurate to predict ischemia (AUC: 0.758, p < 0.001 compared to ESC 2013, 0.661; ESC 2019, 0.673; ACC 2012, 0.585; ACC 2021, 0.667). Using the < 5% threshold, the MPA’s sensitivity and negative predictive value to rule out ischemia were 99.1% and 96.4%, respectively. The model allocated patients more evenly across PTP categories, reduced the proportion of patients in the intermediate (15–85%) range by 29% (ACC 2012)–51% (ESC 2019), and was the only tool to correctly predict ischemia prevalence in the very low PTP category.ConclusionThe MPA model enhanced ischemia testing according to the PPPM framework:The MPA model improved individual prediction of ischemia significantly and could safely exclude ischemia based on readily available variables without advanced testing (“predictive”).It reduced the proportion of patients in the intermediate PTP range. Therefore, it could be used as a gatekeeper to prevent patients from further unnecessary downstream testing, radiation exposure and costs (“preventive”).Consequently, the MPA model could transform ischemia testing towards a more personalised diagnostic algorithm (“personalised”).

Predicting 1-, 3-, 5-, and 8-year all-cause mortality in a community-dwelling older adult cohort: relevance for predictive, preventive, and personalized medicine

BackgroundPopulation aging is a global public health issue involving increased prevalence of age-related diseases, and concomitant burden on medical resources and the economy. Ninety-two diseases have been identified as age-related, accounting for 51.3% of the global adult disease burden. The economic cost per capita for older people over 60 years is 10 times that of the younger population. From the aspects of predictive, preventive, and personalized medicine (PPPM), developing a risk-prediction model can help identify individuals at high risk for all-cause mortality and provide an opportunity for targeted prevention through personalized intervention at an early stage. However, there is still a lack of predictive models to help community-dwelling older adults do well in healthcare.ObjectivesThis study aims to develop an accurate 1-, 3-, 5-, and 8-year all-cause mortality risk-prediction model by using clinical multidimensional variables, and investigate risk factors for 1-, 3-, 5-, and 8-year all-cause mortality in community-dwelling older adults to guide primary prevention.MethodsThis is a two-center cohort study. Inclusion criteria: (1) community-dwelling adult, (2) resided in the districts of Chaonan or Haojiang for more than 6 months in the past 12 months, and (3) completed a health examination. Exclusion criteria: (1) age less than 60 years, (2) more than 30 incomplete variables, (3) no signed informed consent. The primary outcome of the study was all-cause mortality obtained from face-to-face interviews, telephone interviews, and the medical death database from 2012 to 2021. Finally, we enrolled 5085 community-dwelling adults, 60 years and older, who underwent routine health screening in the Chaonan and Haojiang districts, southern China, from 2012 to 2021. Of them, 3091 participants from Chaonan were recruited as the primary training and internal validation study cohort, while 1994 participants from Haojiang were recruited as the external validation cohort. A total of 95 clinical multidimensional variables, including demographics, lifestyle behaviors, symptoms, medical history, family history, physical examination, laboratory tests, and electrocardiogram (ECG) data were collected to identify candidate risk factors and characteristics. Risk factors were identified using least absolute shrinkage and selection operator (LASSO) models and multivariable Cox proportional hazards regression analysis. A nomogram predictive model for 1-, 3-, 5- and 8-year all-cause mortality was constructed. The accuracy and calibration of the nomogram prediction model were assessed using the concordance index (C-index), integrated Brier score (IBS), receiver operating characteristic (ROC), and calibration curves. The clinical validity of the model was assessed using decision curve analysis (DCA).ResultsNine independent risk factors for 1-, 3-, 5-, and 8-year all-cause mortality were identified, including increased age, male, alcohol status, higher daily liquor consumption, history of cancer, elevated fasting glucose, lower hemoglobin, higher heart rate, and the occurrence of heart block. The acquisition of risk factor criteria is low cost, easily obtained, convenient for clinical application, and provides new insights and targets for the development of personalized prevention and interventions for high-risk individuals. The areas under the curve (AUC) of the nomogram model were 0.767, 0.776, and 0.806, and the C-indexes were 0.765, 0.775, and 0.797, in the training, internal validation, and external validation sets, respectively. The IBS was less than 0.25, which indicates good calibration. Calibration and decision curves showed that the predicted probabilities were in good agreement with the actual probabilities and had good clinical predictive value for PPPM.ConclusionThe personalized risk prediction model can identify individuals at high risk of all-cause mortality, help offer primary care to prevent all-cause mortality, and provide personalized medical treatment for these high-risk individuals from the PPPM perspective. Strict control of daily liquor consumption, lowering fasting glucose, raising hemoglobin, controlling heart rate, and treatment of heart block could be beneficial for improving survival in elderly populations.

Performance Evaluation of Machine Learning Algorithms for Sarcopenia Diagnosis in Older Adults.

Sarcopenia is a progressive and generalized skeletal muscle disorder. Early diagnosis is necessary to reduce the adverse effects and consequences of sarcopenia, which can help prevent and manage it in a timely manner. The aim of this study was to identify the important risk factors for sarcopenia diagnosis and compare the performance of machine learning (ML) algorithms in the early detection of potential sarcopenia. A cross-sectional design was employed for this study, involving 160 participants aged 65 years and over who resided in a community. ML algorithms were applied by selecting 11 features-sex, age, BMI, presence of hypertension, presence of diabetes mellitus, SARC-F score, MNA score, calf circumference (CC), gait speed, handgrip strength (HS), and mid-upper arm circumference (MUAC)-from a pool of 107 clinical variables. The results of the three best-performing algorithms were presented. The highest accuracy values were achieved by the ALL (male + female) model using LightGBM (0.931), random forest (RF; 0.927), and XGBoost (0.922) algorithms. In the female model, the support vector machine (SVM; 0.939), RF (0.923), and k-nearest neighbors (KNN; 0.917) algorithms performed the best. Regarding variable importance in the ALL model, the last HS, sex, BMI, and MUAC variables had the highest values. In the female model, these variables were HS, age, MUAC, and BMI, respectively. Machine learning algorithms have the ability to extract valuable insights from data structures, enabling accurate predictions for the early detection of sarcopenia. These predictions can assist clinicians in the context of predictive, preventive, and personalized medicine (PPPM).

Multi-omics analysis reveals that ferroptosis-related gene CISD2 is a prognostic biomarker of head and neck squamous cell carcinoma.

Head and neck squamous cell carcinoma (HNSCC) is a prevalent malignancy, with high mortality rate and unavailability of accurate therapies. However, its early prevention remains a challenge. In the purview of predictive, preventive, and personalized medicine (PPPM), it is paramount to identify novel and powerful biomarkers. CISD2 is a crucial regulator of iron homeostasis and reactive oxygen species (ROS). Recent studies showed that the NEET protein (NAF-1) encoded by CISD2 is involved in regulating the proliferation and metastasis of tumor cells. Nevertheless, the prognostic value and immunological correlations of CISD2 remain unclear. Bioinformatics analyses conducted utilizing data from comprehensive databases The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO). All statistical evaluations were executed employing R software. Our investigation of biological function, enrichment pathway, and immune correlation revealed a discernable linkage between CISD2 and the immune response. Moreover, we found that the suppression of CISD2 is associated with immune cell infiltration and various immune signatures. The present study successfully revealed the potential prognostic and biological function of CISD2 in HNSCC. High expression of CISD2 are linked to gender, race, grade, etc., can notably enhance the early detection, prognosis, and prediction for individuals afflicted with HNSCC.

Quantitative phosphoproteomics reveals molecular pathway network alterations in human early-stage primary hepatic carcinomas: potential for 3P medical approach.

Hepatic carcinoma is one of the most common types of malignant tumors in the digestive system, and its biological characteristics determine its high rate of metastasis and recurrence after radical resection, leading to a poor prognosis for patients. Increasing evidence demonstrates that phosphoproteins and phosphorylation-mediated molecular pathways influence the occurrence and development of hepatic carcinoma. It is urgent need to develop early-stage biomarkers for improving diagnosis, therapy, medical service, and prognostic assessment. We hypothesize that phosphoproteome and phosphorylation-mediated signaling pathway networks significantly differ in human early-stage primary hepatic carcinomas relative to control liver tissues, which will identify the key differentially phosphorylated proteins and phosphorylation-mediated signaling pathway network alterations in human early-stage primary hepatic carcinoma to innovate predictive diagnosis, prognostic assessment, and personalized medical services and progress beyond the state of the art in the framework of predictive, preventive, and personalized medicine (PPPM). Tandem mass tag (TMT)-based quantitative proteomics coupled with TiO2 enrichment of phosphopeptides was used to identify phosphorylation profiling, and bioinformatics was used to analyze the pathways and biological functions of phosphorylation profiling between early-stage hepatic carcinoma tissues and tumor-adjacent normal control tissues. Furthermore, the integrative analysis with transcriptomic data from TCGA database obtained differently expressed genes (DEGs) corresponding to differentially phosphorylated proteins (DPPs) and overall survival (OS)-related DPPs. A total of 1326 phosphopeptides derived from 858 DPPs in human early-stage primary hepatic carcinoma were identified. KEGG pathway network analysis of 858 DPPs revealed 33 statistically significant signaling pathways, including spliceosome, glycolysis/gluconeogenesis, B-cell receptor signaling pathway, HIF-1 signaling pathway, and fatty acid degradation. Gene Ontology (GO) analysis of 858 DPPs revealed that protein phosphorylation was involved in 57 biological processes, 40 cellular components, and 37 molecular functions. Protein-protein interaction (PPI) network constructed multiple high-combined scores and co-expressed DPPs. Integrative analysis of transcriptomic data and DPP data identified 105 overlapped molecules (DPPs; DEGs) between hepatic carcinoma tissues and control tissues and 125 OS-related DPPs. Overlapping Venn plots showed 14 common molecules among datasets of DPPs, DEGs, and OS-related DDPs, including FTCD, NDRG2, CCT2, PECR, SLC23A2, PNPLA7, ANLN, HNRNPM, HJURP, MCM2, STMN1, TCOF1, TOP2A, and SSRP1. The drug sensitivities of OS-related DPPs were identified, including LMOD1, CAV2, UBE2E2, RAPH1, ANXA5, HDLBP, CUEDC1, APBB1IP, VCL, SRSF10, SLC23A2, EPB41L2, ESR1, PLEKHA4, SAFB2, SMARCAD1, VCAN, PSD4, RDH16, NOP56, MEF2C, BAIAP2L2, NAGS, SRSF2, FHOD3, and STMN1. Identification and annotation of phosphoproteomes and phosphorylation-mediated signaling pathways in human early-stage primary hepatic carcinoma tissues provided new directions for tumor prevention and treatment, which (i) helps to enrich phosphorylation functional research and develop new biomarkers; (ii) enriches phosphorylation-mediated signaling pathways to gain a deeper understanding of the underlying mechanisms of early-stage primary hepatic carcinoma; and (iii) develops anti-tumor drugs that facilitate targeted phosphorylated sites. We recommend quantitative phosphoproteomics in early-stage primary hepatic carcinoma, which offers great promise for in-depth insight into the molecular mechanism of early-stage primary hepatic carcinoma, the discovery of effective therapeutic targets/drugs, and the construction of reliable phosphorylation-related biomarkers for patient stratification, predictive diagnosis, prognostic assessment, and personalized medical services in the framework of PPPM. The online version contains supplementary material available at 10.1007/s13167-023-00335-3.

COVID-19 lessons to protect populations against future pandemics by implementing PPPM principles in healthcare.

The coronavirus disease 2019 (COVID-19) pandemic has continued for more than 3years, placing a huge burden on society worldwide. Although the World Health Organization (WHO) has declared an end to COVID-19 as a Public Health Emergency of International Concern (PHEIC), it is still considered a global threat. Previously, there has been a long debate as to whether the COVID-19 emergency will eventually end or transform into a more common infectious disease from a PHEIC, and how should countries respond to similar pandemics in the future more time-efficiently and cost-effectively. We reviewed the past, middle and current situation of COVID-19 based on bibliometric analysis and epidemiological data. Thereby, the necessity is indicated to change the paradigm from reactive healthcare services to predictive, preventive and personalised medicine (PPPM) approach, in order to effectively protect populations against COVID-19 and any future pandemics. Corresponding measures are detailed in the article including the involvement of multi-professional expertise, application of artificial intelligence, rapid diagnostics and patient stratification, and effective protection, amongst other to be considered by advanced health policy.

Anatomic characteristics of shoulder based on MRI accurately predict incomplete rotator cuff injuries in patients: relevance for predictive, preventive, and personalized healthcare strategies.

In the diagnosis of incomplete rotator cuff injuries (IRCI), magnetic resonance imaging (MRI) and ultrasound examination often have false-positive and false-negative results, while arthroscopy is expensive, invasive, and complex. From the strategy of predictive, preventive, and personalized medicine (PPPM), shoulder anatomical characteristics based on MRI have been demonstrated to accurately predict IRCI and their clinical applicability for personalized prediction of IRCI. This study aimed to develop and validate a nomogram based on anatomical features of the shoulder on MRI to identify IRCI for PPPM healthcare strategies. The medical information of 257 patients undergoing preoperative MRI examination was retrospectively reviewed and served as the primary cohort. Partial-thickness rotator cuff tears (RCTs) and tendinopathy observed under arthroscopy were considered IRCI. Using logistic regression analyses and least absolute shrinkage and selection operator (LASSO), IRCI was identified among various preoperative factors containing shoulder MRI and clinical features. A nomogram was constructed and subjected to internal and external validations (80 patients). The following eight independent risk factors for IRCI were identified:AgeThe left injured sidesThe Goutallier classification of supraspinatus in oblique coronal positionThe Goutallier classification of supraspinatus in the axial positionAcromial thicknessAcromiohumeral distanceCoracohumeral distanceAbnormal acromioclavicular joint signalsThe nomogram accurately predicted IRCI in the development (C-index, 0.932 (95% CI, 0.891, 0.973)) and validation (C-index, 0.955 (95% CI, 0.918, 0.992)) cohorts. The calibration curve was consistent between the predicted IRCI probability and the actual IRCI ratio of the nomogram. The decision curve analysis and clinical impact curves demonstrated that the model had high clinical applicability. Eight independent factors that accurately predicted IRCI were determined using MRI anatomical findings. These personalized factors can prevent unnecessary diagnostic interventions (e.g., arthroscopy) and can assist surgeons in implementing individualized clinical decisions in medical practice, thus addressing the goals of PPPM. The online version contains supplementary material available at 10.1007/s13167-023-00333-5.

Mechanical power normalized to aerated lung predicts noninvasive ventilation failure and death and contributes to the benefits of proning in COVID-19 hypoxemic respiratory failure.

Concern exists that noninvasive ventilation (NIV) may promote ventilation-induced lung injury(VILI) and worsen outcome in acute hypoxemic respiratory failure (AHRF). Different individual ventilatory variables have been proposed to predict clinical outcomes, with inconsistent results.Mechanical power (MP), a measure of the energy transfer rate from the ventilator to the respiratory system during mechanical ventilation, might provide solutions for this issue in the framework of predictive, preventive and personalized medicine(PPPM). We explored (1)the impact of ventilator-delivered MP normalized to well-aerated lung(MPWAL) on physio-anatomical and clinical responses to NIV in COVID-19-related AHRF and (2)the effect of prone position(PP) on MPWAL. We analyzed 216 noninvasively ventilated COVID-19 patients (108 patients receiving PP + NIV and 108 propensity score-matched patients receiving supine NIV) with moderate-to-severe(paO2/FiO2 ratio < 200) AHRF enrolled in the PRO-NIV controlled non-randomized study(ISRCTN23016116).Quantification of differentially aerated lung volumes by lung ultrasonography (LUS) was validated against CT scans. Respiratory parameters were hourly recorded, ABG were performed 1h after each postural change. Time-weighed average values of ventilatory variables, including MPWAL, and gas exchange parameters(paO2/FiO2 ratio, dead space indices) were calculated for each ventilatory session. LUS and circulating biomarkers were assessed daily. Compared with supine position, PP was associated with a 34% MPWAL reduction, attributable largely to an absolute MP reduction and secondly to an enhanced lung reaeration.Patients receiving a high MPWAL during the 1st 24h of NIV [MPWAL(day 1)] had higher 28-d NIV failure (HR = 4.33,95%CI:3.09 - 5.98) and death (HR = 5.17,95%CI: 3.01 - 7.35) risks than those receiving a low MPWAL(day 1).In Cox multivariate analyses, MPWAL(day 1) remained independently associated with 28-d NIV failure(HR = 1.68,95%CI:1.15-2.41) and death (HR = 1.69,95%CI:1.22-2.32).MPWAL(day 1) outperformed other power measures and ventilatory variables as predictor of 28-d NIV failure(AUROC = 0.89;95%CI:0.85-0.93) and death (AUROC = 0.89;95%CI:0.85-0.94).MPWAL(day 1) predicted also gas exchange, ultrasonographic and inflammatory biomarker responses, as markers of VILI, on linear multivariate analysis. In the framework of PPPM, early bedside MPWAL calculation may provide added value to predict response to NIV and guide subsequent therapeutic choices i.e. prone position adoption during NIV or upgrading to invasive ventilation, to reduce hazardous MPWAL delivery, prevent VILI progression and improve clinical outcomes in COVID-19-related AHRF. The online version contains supplementary material available at 10.1007/s13167-023-00325-5.

Clarifying the effect of gut microbiota on allergic conjunctivitis risk is instrumental for predictive, preventive, and personalized medicine: a Mendelian randomization analysis.

Allergic conjunctivitis is an ocular immune disease which affects the conjunctiva, eyelids, and cornea. Growing evidence implicates the gut microbiota in balancing and modulating immunity response, and in the pathogenesis of allergic disease. As a result, gut microbial imbalance could be a useful indicator for allergic conjunctivitis. From the perspective of predictive, preventive, and personalized medicine (PPPM), clarifying the role of gut microbial imbalance in the development of allergic conjunctivitis could provide a window of opportunity for primary prediction, targeted prevention, and personalized treatment of the disease. In our study, we hypothesized that individuals with microbial dysbiosis may be more susceptible to allergic conjunctivitis due to an increased inflammatory response. To verify the working hypothesis, our analysis selected genetic variants linked with gut microbiota features (N = 18,340) and allergic conjunctivitis (4513 cases, 649,376 controls) from genome-wide association studies. The inverse-variance weighted (IVW) estimate, Mendelian randomization (MR)-Egger, weighted median estimator, maximum likelihood estimator (MLE), and MR robust adjusted profile score (MR.RAPS) were employed to analyze the impact of gut microbiota on the risk of allergic conjunctivitis and identify allergic conjunctivitis-related gut microbes. Ultimately, these findings may enable the identification of individuals at risk of allergic conjunctivitis through screening of gut microbial imbalances, and allow for new targeted prevention and personalized treatment strategies. Genetic liability to Ruminococcaceae_UCG_002 (OR, 0.83; 95% CI, 0.70-0.99; P = 4.04×10-2), Holdemanella (OR, 0.78; 95% CI, 0.64-0.96; P = 2.04×10-2), Catenibacterium (OR, 0.69; 95% CI, 0.56-0.86; P = 1.09×10-3), Senegalimassilia (OR, 0.71; 95% CI, 0.55-0.93; P = 1.23×10-2) genus were associated with a low risk of allergic conjunctivitis with IVW. Besides, we found suggestive associations of a genetic-driven increase in the Oscillospira (OR, 1.41; 95% CI, 1.00-2.00; P = 4.63×10-2) genus with a higher risk of allergic conjunctivitis. Moreover, MLE and MR.RAPS show consistent results with IVW after further validation and strengthened confidence in the true causal associations. No heterogeneity and pleiotropy was detected. Our study suggests that gut microbiota may play a causal role in the development of allergic conjunctivitis and provides new insights into the microbiota-mediated mechanism of the disease. Gut microbiota may serve as a target for future predictive diagnostics, targeted prevention, and individualized therapy in allergic conjunctivitis, facilitating the transition from reactive medical services to PPPM in the management of the disease. The online version contains supplementary material available at 10.1007/s13167-023-00321-9.

Multi-omics and immune cells' profiling of COVID-19 patients for ICU admission prediction: in silico analysis and an integrated machine learning-based approach in the framework of Predictive, Preventive, and Personalized Medicine.

Intensive care unit admission (ICUA) triage has been urgent need for solving the shortage of ICU beds, during the coronavirus disease 2019 (COVID-19) surge. In silico analysis and integrated machine learning (ML) approach, based on multi-omics and immune cells (ICs) profiling, might provide solutions for this issue in the framework of predictive, preventive, and personalized medicine (PPPM). Multi-omics was used to screen the synchronous differentially expressed protein-coding genes (SDEpcGs), and an integrated ML approach to develop and validate a nomogram for prediction of ICUA. Finally, the independent risk factor (IRF) with ICs profiling of the ICUA was identified. Colony-stimulating factor 1 receptor (CSF1R) and peptidase inhibitor 16 (PI16) were identified as SDEpcGs, and each fold change (FCij) of CSF1R and PI16 was selected to develop and validate a nomogram to predict ICUA. The area under curve (AUC) of the nomogram was 0.872 (95% confidence interval (CI): 0.707 to 0.950) on the training set, and 0.822 (95% CI: 0.659 to 0.917) on the testing set. CSF1R was identified as an IRF of ICUA, expressed in and positively correlated with monocytes which had a lower fraction in COVID-19 ICU patients. The nomogram and monocytes could provide added value to ICUA prediction and targeted prevention, which are cost-effective platform for personalized medicine of COVID-19 patients. The log2fold change (log2FC) of the fraction of monocytes could be monitored simply and economically in primary care, and the nomogram offered an accurate prediction for secondary care in the framework of PPPM. The online version contains supplementary material available at 10.1007/s13167-023-00317-5.

Identification and characterization of a novel molecular classification incorporating oxidative stress and metabolism-related genes for stomach adenocarcinoma in the framework of predictive, preventive, and personalized medicine.

Stomach adenocarcinoma (STAD) is one of the primary contributors to deaths that are due to cancer globally. At the moment, STAD does not have any universally acknowledged biological markers, and its predictive, preventive, and personalized medicine (PPPM) remains sufficient. Oxidative stress can promote cancer by increasing mutagenicity, genomic instability, cell survival, proliferation, and stress resistance pathways. As a direct and indirect result of oncogenic mutations, cancer depends on cellular metabolic reprogramming. However, their roles in STAD remain unclear. 743 STAD samples from GEO and TCGA platforms were selected. Oxidative stress and metabolism-related genes (OMRGs) were acquired from the GeneCard Database. A pan-cancer analysis of 22 OMRGs was first performed. We categorized STAD samples by OMRG mRNA levels. Additionally, we explored the link between oxidative metabolism scores and prognosis, immune checkpoints, immune cell infiltration, and sensitivity to targeted drugs. A series of bioinformatics technologies were employed to further construct the OMRG-based prognostic model and clinical-associated nomogram. We identified 22 OMRGs that could evaluate the prognoses of patients with STAD. Pan-cancer analysis concluded and highlighted the crucial part of OMRGs in the appearance and development of STAD. Subsequently, 743 STAD samples were categorized into three clusters with the enrichment scores being C2 (upregulated) > C3 (normal) > C1 (downregulated). Patients in C2 had the lowest OS rate, while C1 had the opposite. Oxidative metabolic score significantly correlates with immune cells and immune checkpoints. Drug sensitivity results reveal that a more tailored treatment can be designed based on OMRG. The OMRG-based molecular signature and clinical nomogram have good accuracy for predicting the adverse events of patients with STAD. Both transcriptional and translational levels of ANXA5, APOD, and SLC25A15 exhibited significantly higher in STAD samples. The OMRG clusters and risk model accurately predicted prognosis and personalized medicine. Based on this model, high-risk patients might be identified in the early stage so that they can receive specialized care and preventative measures, and choose targeted drug beneficiaries to deliver individualized medical services. Our results showed oxidative metabolism in STAD and led to a new route for improving PPPM for STAD.

Integrating oculomics with genomics reveals imaging biomarkers for preventive and personalized prediction of arterial aneurysms

ObjectiveArterial aneurysms are life-threatening but usually asymptomatic before requiring hospitalization. Oculomics of retinal vascular features (RVFs) extracted from retinal fundus images can reflect systemic vascular properties and therefore were hypothesized to provide valuable information on detecting the risk of aneurysms. By integrating oculomics with genomics, this study aimed to (i) identify predictive RVFs as imaging biomarkers for aneurysms and (ii) evaluate the value of these RVFs in supporting early detection of aneurysms in the context of predictive, preventive and personalized medicine (PPPM).MethodsThis study involved 51,597 UK Biobank participants who had retinal images available to extract oculomics of RVFs. Phenome-wide association analyses (PheWASs) were conducted to identify RVFs associated with the genetic risks of the main types of aneurysms, including abdominal aortic aneurysm (AAA), thoracic aneurysm (TAA), intracranial aneurysm (ICA) and Marfan syndrome (MFS). An aneurysm-RVF model was then developed to predict future aneurysms. The performance of the model was assessed in both derivation and validation cohorts and was compared with other models employing clinical risk factors. An RVF risk score was derived from our aneurysm-RVF model to identify patients with an increased risk of aneurysms.ResultsPheWAS identified a total of 32 RVFs that were significantly associated with the genetic risks of aneurysms. Of these, the number of vessels in the optic disc (‘ntreeA’) was associated with both AAA (β = −0.36, P = 6.75e−10) and ICA (β = −0.11, P = 5.51e−06). In addition, the mean angles between each artery branch (‘curveangle_mean_a’) were commonly associated with 4 MFS genes (FBN1: β = −0.10, P = 1.63e−12; COL16A1: β = −0.07, P = 3.14e−09; LOC105373592: β = −0.06, P = 1.89e−05; C8orf81/LOC441376: β = 0.07, P = 1.02e−05). The developed aneurysm-RVF model showed good discrimination ability in predicting the risks of aneurysms. In the derivation cohort, the C-index of the aneurysm-RVF model was 0.809 [95% CI: 0.780–0.838], which was similar to the clinical risk model (0.806 [0.778–0.834]) but higher than the baseline model (0.739 [0.733–0.746]). Similar performance was observed in the validation cohort, with a C-index of 0.798 (0.727–0.869) for the aneurysm-RVF model, 0.795 (0.718–0.871) for the clinical risk model and 0.719 (0.620–0.816) for the baseline model. An aneurysm risk score was derived from the aneurysm-RVF model for each study participant. The individuals in the upper tertile of the aneurysm risk score had a significantly higher risk of aneurysm compared to those in the lower tertile (hazard ratio = 17.8 [6.5–48.8], P = 1.02e−05).ConclusionWe identified a significant association between certain RVFs and the risk of aneurysms and revealed the impressive capability of using RVFs to predict the future risk of aneurysms by a PPPM approach. Our finds have great potential to support not only the predictive diagnosis of aneurysms but also a preventive and more personalized screening plan which may benefit both patients and the healthcare system.Graphical abstract

Diagnostic accuracy of autoverification and guidance system for COVID-19 RT-PCR results

BackgroundTo date, most countries worldwide have declared that the pandemic of COVID-19 is over, while the WHO has not officially ended the COVID-19 pandemic, and China still insists on the personalized dynamic COVID-free policy. Large-scale nucleic acid testing in Chinese communities and the manual interpretation for SARS-CoV-2 nucleic acid detection results pose a huge challenge for labour, quality and turnaround time (TAT) requirements. To solve this specific issue while increase the efficiency and accuracy of interpretation, we created an autoverification and guidance system (AGS) that can automatically interpret and report the COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR) results relaying on computer-based autoverification procedure and then validated its performance in real-world environments. This would be conductive to transmission risk prediction, COVID-19 prevention and control and timely medical treatment for positive patients in the context of the predictive, preventive and personalized medicine (PPPM).MethodsA diagnostic accuracy test was conducted with 380,693 participants from two COVID-19 test sites in China, the Hong Kong Hybribio Medical Laboratory (n = 266,035) and the mobile medical shelter at a Shanghai airport (n = 114,658). These participants underwent SARS-CoV-2 RT-PCR from March 28 to April 10, 2022. All RT-PCR results were interpreted by laboratorians and by using AGS simultaneously. Considering the manual interpretation as gold standard, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy were applied to evaluate the diagnostic value of the AGS on the interpretation of RT-PCR results.ResultsAmong the 266,035 samples in Hong Kong, there were 16,356 (6.15%) positive, 231,073 (86.86%) negative, 18,606 (6.99%) indefinite, 231,073 (86.86%, negative) no retest required and 34,962 (13.14%, positive and indefinite) retest required; the 114,658 samples in Shanghai consisted of 76 (0.07%) positive, 109,956 (95.90%) negative, 4626 (4.03%) indefinite, 109,956 (95.90%, negative) no retest required and 4702 (4.10%, positive and indefinite) retest required. Compared to the fashioned manual interpretation, the AGS is a procedure of high accuracy [99.96% (95%CI, 99.95–99.97%) in Hong Kong and 100% (95%CI, 100–100%) in Shanghai] with perfect sensitivity [99.98% (95%CI, 99.97–99.98%) in Hong Kong and 100% (95%CI, 100–100%) in Shanghai], specificity [99.87% (95%CI, 99.82–99.90%) in Hong Kong and 100% (95%CI, 99.92–100%) in Shanghai], PPV [99.98% (95%CI, 99.97–99.99%) in Hong Kong and 100% (95%CI, 99.99–100%) in Shanghai] and NPV [99.85% (95%CI, 99.80–99.88%) in Hong Kong and 100% (95%CI, 99.90–100%) in Shanghai]. The need for manual interpretation of total samples was dramatically reduced from 100% to 13.1% and the interpretation time fell from 53 h to 26 min in Hong Kong; while the manual interpretation of total samples was decreased from 100% to 4.1% and the interpretation time dropped from 20 h to 16 min at Shanghai.ConclusionsThe AGS is a procedure of high accuracy and significantly relieves both labour and time from the challenge of large-scale screening of SARS-CoV-2 using RT-PCR. It should be recommended as a powerful screening, diagnostic and predictive system for SARS-CoV-2 to contribute timely the ending of the COVID-19 pandemic following the concept of PPPM.

Global burden of cancers attributable to tobacco smoking, 1990-2019: an ecological study.

Identifying risk factors for cancer initiation and progression is the cornerstone of the preventive approach to cancer management and control (EPMA J. 4(1):6, 2013). Tobacco smoking is a well-recognized risk factor for initiation and spread of several cancers. The predictive, preventive, and personalized medicine (PPPM) approach to cancer management and control focuses on smoking cessation as an essential cancer prevention strategy. Towards this end, this study examines the temporal patterns of cancer burden due to tobacco smoking in the last three decades at global, regional, and national levels. The data pertaining to the burden of 16 cancers attributable to tobacco smoking at global, regional, and national levels were procured from the Global Burden of Disease 2019 Study. Two main indicators, deaths and disability-adjusted life years (DALYs), were used to describe the burden of cancers attributable to tobacco smoking. The socio-economic development of countries was measured using the socio-demographic index (SDI). Globally, deaths due to neoplasms caused by tobacco smoking increased from 1.5 million in 1990 to 2.5 million in 2019, whereas the age-standardized mortality rate (ASMR) decreased from 39.8/100,000 to 30.6/100,000 and the age-standardized DALY rate (ASDALR) decreased from 948.9/100,000 to 677.3/100,000 between 1990 and 2019. Males accounted for approximately80% of globaldeaths and DALYs in 2019. Populous regions of Asia and a few regions of Europe account for the largest absolute burden, whereas countries in Europe and America have the highest age-standardized ratesof cancers due to tobacco smoking. In 8 out of 21 regions, there were more than 100,000 deaths due to cancers attributable to tobacco smoking led by East Asia, followed by Western Europe in 2019. The regions of Sub-Saharan Africa (except southern region) had one of the lowest absolute counts of deaths, DALYs, and age-standardized rates. In 2019, tracheal, bronchus, and lung (TBL), esophageal, stomach, colorectal, and pancreatic cancer were the top 5 neoplasms attributable to tobacco smoking, with different burdens in regions as per their development status. The ASMR and ASDALR of neoplasms due to tobacco smoking were positively correlated with SDI, with pairwise correlation coefficient of 0.55 and 0.52, respectively. As a preventive tool, tobacco smoking cessation has the biggest potential among all risk factors for preventing millions of cancer deaths every year. Cancer burden due to tobacco smoking is found to be higher in males and is positively associated with socio-economic development of countries. As tobacco smoking begins mostly at younger ages and the epidemic is unfolding in several parts of the world, more accelerated efforts are required towards tobacco cessation and preventing youth from entering this addiction. The PPPM approach to medicine suggests that not only personalized and precision medicine must be provided to cancer patients afflicted by tobacco smoking but personalized and targeted preventive solutions must be provided to prevent initiation and progression of smoking. The online version contains supplementary material available at 10.1007/s13167-022-00308-y.

Predictive, preventive, and personalized management of retinal fluid via computer-aided detection app for optical coherence tomography scans.

Computer-aided detection systems for retinal fluid could be beneficial for disease monitoring and management by chronic age-related macular degeneration (AMD) and diabetic retinopathy (DR) patients, to assist in disease prevention via early detection before the disease progresses to a "wet AMD" pathology or diabetic macular edema (DME), requiring treatment. We propose a proof-of-concept AI-based app to help predict fluid via a "fluid score", prevent fluid progression, and provide personalized, serial monitoring, in the context of predictive, preventive, and personalized medicine (PPPM) for patients at risk of retinal fluid complications. The app comprises a convolutional neural network-Vision Transformer (CNN-ViT)-based segmentation deep learning (DL) network, trained on a small dataset of 100 training images (augmented to 992 images) from the Singapore Epidemiology of Eye Diseases (SEED) study, together with a CNN-based classification network trained on 8497 images, that can detect fluid vs. non-fluid optical coherence tomography (OCT) scans. Both networks are validated on external datasets. Internal testing for our segmentation network produced an IoU score of 83.0% (95% CI = 76.7-89.3%) and a DICE score of 90.4% (86.3-94.4%); for external testing, we obtained an IoU score of 66.7% (63.5-70.0%) and a DICE score of 78.7% (76.0-81.4%). Internal testing of our classification network produced an area under the receiver operating characteristics curve (AUC) of 99.18%, and a Youden index threshold of 0.3806; for external testing, we obtained an AUC of 94.55%, and an accuracy of 94.98% and an F1 score of 85.73% with Youden index. We have developed an AI-based app with an alternative transformer-based segmentation algorithm that could potentially be applied in the clinic with a PPPM approach for serial monitoring, and could allow for the generation of retrospective data to research into the varied use of treatments for AMD and DR. The modular system of our app can be scaled to add more iterative features based on user feedback for more efficient monitoring. Further study and scaling up of the algorithm dataset could potentially boost its usability in a real-world clinical setting. The online version contains supplementary material available at 10.1007/s13167-022-00301-5.

Radiomics based on readout-segmented echo-planar imaging (RS-EPI) diffusion-weighted imaging (DWI) for prognostic risk stratification of patients with rectal cancer: a two-centre, machine learning study using the framework of predictive, preventive, and personalized medicine

BackgroundCurrently, the rate of recurrence or metastasis (ROM) remains high in rectal cancer (RC) patients treated with the standard regimen. The potential of diffusion-weighted imaging (DWI) in predicting ROM risk has been reported, but the efficacy is insufficient.AimsThis study investigated the potential of a new sequence called readout-segmented echo-planar imaging (RS-EPI) DWI in predicting the ROM risk of patients with RC using machine learning methods to achieve the principle of predictive, preventive, and personalized medicine (PPPM) application in RC treatment.MethodsA total of 195 RC patients from two centres who directly received total mesorectal excision were retrospectively enrolled in our study. Machine learning methods, including recursive feature elimination (RFE), the synthetic minority oversampling technique (SMOTE), and the support vector machine (SVM) classifier, were used to construct models based on clinical-pathological factors (clinical model), radiomic features from RS-EPI DWI (radiomics model), and their combination (merged model). The Harrell concordance index (C-index) and the area under the time-dependent receiver operating characteristic curve (AUC) were calculated to evaluate the predictive performance at 1 year, 3 years, and 5 years. Kaplan‒Meier analysis was performed to evaluate the ability to stratify patients according to the risk of ROM.FindingsThe merged model performed well in predicting tumour ROM in patients with RC at 1 year, 3 years, and 5 years in both cohorts (AUC = 0.887/0.813/0.794; 0.819/0.795/0.783) and was significantly superior to the clinical model (AUC = 0.87 [95% CI: 0.80–0.93] vs. 0.71 [95% CI: 0.59–0.81], p = 0.009; C-index = 0.83 [95% CI: 0.76–0.90] vs. 0.68 [95% CI: 0.56–0.79], p = 0.002). It also had a significant ability to differentiate patients with a high and low risk of ROM (HR = 12.189 [95% CI: 4.976–29.853], p < 0.001; HR = 6.427 [95% CI: 2.265–13.036], p = 0.002).ConclusionOur developed merged model based on RS-EPI DWI accurately predicted and effectively stratified patients with RC according to the ROM risk at an early stage with an individualized profile, which may be able to assist physicians in individualizing the treatment protocols and promote a meaningful paradigm shift in RC treatment from traditional reactive medicine to PPPM.

Sleep apnea predicts cardiovascular death in patients with Marfan syndrome: a cohort study

BackgroundSurgical replacement of the aortic root is the only intervention that can prevent aortic dissection and cardiovascular death in Marfan syndrome (MFS). However, in some individuals, MFS also causes sleep apnea. If sleep apnea predicts cardiovascular death, a new target for predictive, preventive, and personalized medicine (PPPM) may emerge for those individuals with MFS who have sleep apnea.MethodsThis is an investigator-initiated study with long-term follow-up data of 105 individuals with MFS. All individuals were screened for sleep apnea regardless of symptoms. Cardiovascular death served as a primary endpoint, and aortic events as a secondary outcome.ResultsSleep apnea with an apnea–hypopnea index (AHI) > 5/h was observed in 21.0% (22/105) with mild sleep apnea in 13% (14/105) and moderate to severe sleep apnea in 7.6% (8/105). After a median follow-up of 7.76 years (interquartile range: 6.84, 8.41), 10% (10/105) had died, with cardiovascular cause of death in 80% (8/10). After adjusting for age and body mass index (BMI), the AHI score emerged as an independent risk factor for cardiovascular death (hazard ratio 1.712, 95% confidence interval [1.061–2.761], p = 0.0276). The secondary outcome of aortic events occurred in 33% (35/105). There was no effect of the AHI score on aortic events after adjusting for age and BMI (hazard ratio 0.965, 95% confidence interval [0.617–1.509]), possibly due to a high number of patients with prior aortic surgery.InterpretationSleep apnea is emerging as an independent predictor of cardiovascular death in MFS. It seems mandatory to screen all individuals with MFS for sleep apnea and to include these individuals, with both MFS and sleep apnea, in further studies to evaluate the impact of preventive measures with regard to cardiovascular death.

Identifying potential signatures for atherosclerosis in the context of predictive, preventive, and personalized medicine using integrative bioinformatics approaches and machine-learning strategies.

Atherosclerosis is a major contributor to morbidity and mortality worldwide. Although several molecular markers associated with atherosclerosis have been developed in recent years, the lack of robust evidence hinders their clinical applications. For these reasons, identification of novel and robust biomarkers will directly contribute to atherosclerosis management in the context of predictive, preventive, and personalized medicine (PPPM). This integrative analysis aimed to identify critical genetic markers of atherosclerosis and further explore the underlying molecular immune mechanism attributing to the altered biomarkers. Gene Expression Omnibus (GEO) series datasets were downloaded from GEO. Firstly, differential expression analysis and functional analysis were conducted. Multiple machine-learning strategies were then employed to screen and determine key genetic markers, and receiver operating characteristic (ROC) analysis was used to assess diagnostic value. Subsequently, cell-type identification by estimating relative subsets of RNA transcript (CIBERSORT) and a single-cell RNA sequencing (scRNA-seq) data were performed to explore relationships between signatures and immune cells. Lastly, we validated the biomarkers' expression in human and mice experiments. A total of 611 overlapping differentially expressed genes (DEGs) included 361 upregulated and 250 downregulated genes. Based on the enrichment analysis, DEGs were mapped in terms related to immune cell involvements, immune activating process, and inflaming signals. After using multiple machine-learning strategies, dehydrogenase/reductase 9 (DHRS9) and protein tyrosine phosphatase receptor type J (PTPRJ) were identified as critical biomarkers and presented their high diagnostic accuracy for atherosclerosis. From CIBERSORT analysis, both DHRS9 and PTPRJ were significantly related to diverse immune cells, such as macrophages and mast cells. Further scRNA-seq analysis indicated DHRS9 was specifically upregulated in macrophages of atherosclerotic lesions, which was confirmed in atherosclerotic patients and mice. Our findings are the first to report the involvement of DHRS9 in the atherogenesis, and the proatherogenic effect of DHRS9 is mediated by immune mechanism. In addition, we confirm that DHRS9 is localized in macrophages within atherosclerotic plaques. Therefore, upregulated DHRS9 could be a novel potential target for the future predictive diagnostics, targeted prevention, patient stratification, and personalization of medical services in atherosclerosis. The online version contains supplementary material available at 10.1007/s13167-022-00289-y.

TMEM92 acts as an immune-resistance and prognostic marker in pancreatic cancer from the perspective of predictive, preventive, and personalized medicine.

Pancreatic cancer presents extremely poor prognosis due to the difficulty of early diagnosis, low resection rate, and high rates of recurrence and metastasis. Immune checkpoint blockades have been widely used in many cancer types but showed limited efficacy in pancreatic cancer. The current study aimed to evaluate the landscape of tumor microenvironment (TME) of pancreatic cancer and identify the potential markers of prognosis and immunotherapy efficacy which might contribute to improve the targeted therapy strategy and efficacy in pancreatic cancer in the context of predictive, preventive, and personalized medicine (PPPM). In the current study, a total of 382 pancreatic samples from the datasets of Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) were selected. LM22 gene signature matrix was applied to quantify the fraction of immune cells based on "CIBERSORT" algorithm. Weighted Gene Co-expression Network Analysis (WGCNA) and Molecular Complex Detection (MCODE) algorithm was applied to confirm the hub-network of immune-resistance phenotype. A nomogram model based on COX and Logistic regression was constructed to evaluate the prognostic value and the predictive value of hub-gene in immune-response. The role of transmembrane protein 92 (TMEM92) in regulating cell proliferation was evaluated by MTS assay. Western blot and Real-time PCR were applied to assess the biological effects of PD-L1 inhibition by TMEM92. Moreover, the effect of TMEM92 in immunotherapy was evaluated with PBMC co-culture and by MTS assay. Two tumor-infiltrating immune cell (TIIC) phenotypes were identified and a weighted gene co-expression network was constructed to confirm the 167 gene signatures correlated with immune-resistance TIIC subtype. TMEM92 was further identified as a core gene of 167 gene signature network based on MCODE algorithm. High TMEM92 expression was significantly correlated with unfavorable prognosis, characterizing by immune resistance. A nomogram model and external validation confirmed that TMEM92 was an independent prognostic factor in pancreatic cancer. An elevated tumor mutation burden (TMB), mostly is consistent with commonly mutations of KRAS and TP53, was found in the high TMEM92 group. The predictive role of TMEM92 in immunotherapeutic response was also confirmed by IMvigor210 datasets. In addition, the specific biological roles of TMEM92 in cancer was explored in vitro. The results showed that abnormal overexpression of TMEM92 was significantly associated with the poor survival rate of pancreatic cancer. Moreover, we demonstrated that TMEM92 inhibit tumour immune responses of the anti-PD-1 antibody with PBMC co-culture. The current study explored for the first time the immune-resistance phenotype of pancreatic cancer and identified TMEM92 as an innovative marker in predicting clinical outcomes and immunotherapeutic efficacy. These findings not only help to recognize high-risk and immune-resistance population which could be supplied targeted prevention, but also provide personalized medical services by intervening TMEM92 function to improve the prognosis of pancreatic cancer. In addition, the biological role of TMEM92 might reveal the potential molecular mechanisms of pancreatic cancer and lead to a novel sight for development of a PPPM approach for pancreatic cancer management. The online version contains supplementary material available at 10.1007/s13167-022-00287-0.

Metagenomic analysis of the microbiome of the upper reproductive tract: combating ovarian cancer through predictive, preventive, and personalized medicine

PurposeWe investigated whether ovarian cancer could alter the genital microbiota in a specific way with clinical values. Furthermore, we proposed how such changes could be envisioned in a paradigm of predictive, preventive, and personalized medicine (PPPM).MethodsThe samples were collected using cotton swabs from the cervical, uterine cavity, fallopian tubes, and ovaries of patients subjected to the surgical procedures for the malignant/benign lesions. All samples were then analyzed by metagenomic shotgun sequencing. The distribution patterns and characteristics of the microbiota in the reproductive tract of subjects were analyzed and were interpreted in relation to the clinical outcomes of the subjects.ResultsWhile the ovarian cancer was able to alter the genital microbiota, the bacteria were the dominant microorganisms in all samples across all cohorts in the study (median 99%). The microbiota of the upper female reproductive tract were mainly from the cervical, identified by low bacterial biomass and high bacterial diversity. Ovarian cancer had a distinct microbiota signature. The tubal ligation affects its microbial distribution. There were no different species on the surface of platinum-sensitive ovarian tissues compared to samples from platinum-resistant patients.ConclusionThe ovarian cancer–induced changes in microbiota magnify the potential of microbiota as a biotherapeutic modality in the treatment of ovarian cancer in this study and very likely for several malignancies and other conditions. Our findings demonstrated, for the first time, that microbiota could be dissected and applied in more specific fashion based on a predictive, preventive, and personalized medicine (PPPM) model in the treatment of ovarian cancer. Utilizing microbiota portfolio in a PPPM system in ovarian cancer would provide a unique opportunity to a clinically intelligent and novel approach in the treatment of ovarian cancer as well as several other conditions and malignancies.