Traditional Clinical Variables Research Articles

The spatial structure of the tumor immune microenvironment can explain and predict patient response in high-grade serous carcinoma.

Ovarian cancer is the deadliest gynecological malignancy, and therapeutic options and mortality rates over the last three decades have largely not changed. Recent studies indicate that the composition of the tumor immune microenvironment (TIME) influences patient outcomes. To improve spatial understanding of the TIME, we performed multiplexed ion beam imaging on 83 human high-grade serous carcinoma tumor samples, identifying about 160,000 cells across 23 cell types. For 77 of these samples meeting inclusion criteria, we generated composition features based on cell type proportions, spatial features based on the distances between cell types, and spatial network features representing cell interactions and cell clustering patterns, which we linked to traditional clinical and immunohistochemical variables and patient overall survival (OS) and progression-free survival (PFS) outcomes. Among these features, we found several significant univariate correlations, including B-cell contact with M1 macrophages (OS hazard ratio HR=0.696, p=0.011, PFS HR=0.734, p=0.039). We then used high-dimensional random forest models to evaluate out-of-sample predictive performance for OS and PFS outcomes and to derive relative feature importance scores for each feature. The top model for predicting low or high PFS used TIME composition and spatial features and achieved an average AUC (area under the receiver-operating characteristic curve) score of 0.71. The results demonstrate the importance of spatial structure in understanding how the TIME contributes to treatment outcomes. Furthermore, the present study provides a generalizable roadmap for spatial analyses of the TIME in ovarian cancer research.

Pre-treatment radiological factors associated with poor functional outcome in an Asian cohort of large vessel occlusion acute ischemic stroke patients undergoing mechanical thrombectomy.

Endovascular thrombectomy (EVT) is the current standard of care for large vessel occlusion (LVO) acute ischemic stroke (AIS); however, up to two-thirds of EVT patients have poor functional outcomes despite successful reperfusion. Many radiological markers have been studied as predictive biomarkers for patient outcomes in AIS. This study seeks to determine which clinico-radiological factors are associated with outcomes of interest to aid selection of patients for EVT for LVO AIS. A retrospective study of patients who underwent EVT from 2016 to 2020 was performed. Data on various radiological variables, such as anatomical parameters, clot characteristics, collateral status, and infarct size, were collected alongside traditional demographic and clinical variables. Univariate and multivariate analysis was performed for the primary outcomes of functional independence at 3 months post-stroke (modified Rankin Scale 0-2) and secondary outcomes of in-hospital mortality and symptomatic intracranial hemorrhage. The study cohort comprised 325 consecutive patients with anterior circulation LVO AIS (54.5% male) with a median age of 68 years (interquartile range 57-76). The median NIHSS was 19. Age, hypertension, hyperlipidaemia, National Institutes of Health Stroke Scale (NIHSS), Alberta mCTA score, ASPECTS, clot length, thrombus HU and mTICI score and the angle between ICA and CCA were associated with functional outcomes at 3 months on univariate analysis. On multivariate analysis, age, Alberta mCTA collaterals and NIHSS were significantly associated with functional outcomes, while ASPECTS approached significance. Among the many proposed radiological markers for patients in the hyperacute setting undergoing EVT, the existing well-validated clinico-radiological measures remain strongly associated with functional status.

Prediction of Readmission Following Sepsis Using Social Determinants of Health.

To determine the predictive value of social determinants of health (SDoH) variables on 30-day readmission following a sepsis hospitalization as compared with traditional clinical variables. Multicenter retrospective cohort study using patient-level data, including demographic, clinical, and survey data. Thirty-five hospitals across the United States from 2017 to 2021. Two hundred seventy-one thousand four hundred twenty-eight individuals in the AllofUs initiative, of which 8909 had an index sepsis hospitalization. None. Unplanned 30-day readmission to the hospital. Multinomial logistic regression models were constructed to account for survival in determination of variables associate with 30-day readmission and are presented as adjusted odds rations (aORs). Of the 8909 sepsis patients in our cohort, 21% had an unplanned hospital readmission within 30 days. Median age (interquartile range) was 54 years (41-65 yr), 4762 (53.4%) were female, and there were self-reported 1612 (18.09%) Black, 2271 (25.49%) Hispanic, and 4642 (52.1%) White individuals. In multinomial logistic regression models accounting for survival, we identified that change to nonphysician provider type due to economic reasons (aOR, 2.55 [2.35-2.74]), delay of receiving medical care due to lack of transportation (aOR, 1.68 [1.62-1.74]), and inability to afford flow-up care (aOR, 1.59 [1.52-1.66]) were strongly and independently associated with a 30-day readmission when adjusting for survival. Patients who lived in a ZIP code with a high percentage of patients in poverty and without health insurance were also more likely to be readmitted within 30 days (aOR, 1.26 [1.22-1.29] and aOR, 1.28 [1.26-1.29], respectively). Finally, we found that having a primary care provider and health insurance were associated with low odds of an unplanned 30-day readmission. In this multicenter retrospective cohort, several SDoH variables were strongly associated with unplanned 30-day readmission. Models predicting readmission following sepsis hospitalization may benefit from the addition of SDoH factors to traditional clinical variables.

Association between gait video information and general cardiovascular diseases: a prospective cross-sectional study.

Cardiovascular disease (CVD) may not be detected in time with conventional clinical approaches. Abnormal gait patterns have been associated with pathological conditions and can be monitored continuously by gait video. We aim to test the association between non-contact, video-based gait information and general CVD status. Individuals undergoing confirmatory CVD evaluation were included in a prospective, cross-sectional study. Gait videos were recorded with a Kinect camera. Gait features were extracted from gait videos to correlate with the composite and individual components of CVD, including coronary artery disease, peripheral artery disease, heart failure, and cerebrovascular events. The incremental value of incorporating gait information with traditional CVD clinical variables was also evaluated. Three hundred fifty-two participants were included in the final analysis [mean (standard deviation) age, 59.4 (9.8) years; 25.3% were female]. Compared with the baseline clinical variable model [area under the receiver operating curve (AUC) 0.717, (0.690-0.743)], the gait feature model demonstrated statistically better performance [AUC 0.753, (0.726-0.780)] in predicting the composite CVD, with further incremental value when incorporated with the clinical variables [AUC 0.764, (0.741-0.786)]. Notably, gait features exhibited varied association with different CVD component conditions, especially for peripheral artery disease [AUC 0.752, (0.728-0.775)] and heart failure [0.733, (0.707-0.758)]. Additional analyses also revealed association of gait information with CVD risk factors and the established CVD risk score. We demonstrated the association and predictive value of non-contact, video-based gait information for general CVD status. Further studies for gait video-based daily living CVD monitoring are promising.

Assessing recent recurrence after hepatectomy for hepatitis B-related hepatocellular carcinoma by a predictive model based on sarcopenia.

Sarcopenia may be associated with hepatocellular carcinoma (HCC) following hepatectomy. But traditional single clinical variables are still insufficient to predict recurrence. We still lack effective prediction models for recent recurrence (time to recurrence < 2 years) after hepatectomy for HCC. To establish an interventable prediction model to estimate recurrence-free survival (RFS) after hepatectomy for HCC based on sarcopenia. We retrospectively analyzed 283 hepatitis B-related HCC patients who underwent curative hepatectomy for the first time, and the skeletal muscle index at the third lumbar spine was measured by preoperative computed tomography. 94 of these patients were enrolled for external validation. Cox multivariate analysis was per-formed to identify the risk factors of postoperative recurrence in training cohort. A nomogram model was developed to predict the RFS of HCC patients, and its predictive performance was validated. The predictive efficacy of this model was evaluated using the receiver operating characteristic curve. Multivariate analysis showed that sarcopenia [Hazard ratio(HR) = 1.767, 95%CI: 1.166-2.678, P < 0.05], alpha-fetoprotein ≥ 40 ng/mL (HR = 1.984, 95%CI: 1.307-3.011, P < 0.05), the maximum diameter of tumor > 5 cm (HR = 2.222, 95%CI: 1.285-3.842, P < 0.05), and hepatitis B virus DNA level ≥ 2000 IU/mL (HR = 2.1, 95%CI: 1.407-3.135, P < 0.05) were independent risk factors associated with postoperative recurrence of HCC. Based on the sarcopenia to assess the RFS model of hepatectomy with hepatitis B-related liver cancer disease (SAMD) was established combined with other the above risk factors. The area under the curve of the SAMD model was 0.782 (95%CI: 0.705-0.858) in the training cohort (sensitivity 81%, specificity 63%) and 0.773 (95%CI: 0.707-0.838) in the validation cohort. Besides, a SAMD score ≥ 110 was better to distinguish the high-risk group of postoperative recurrence of HCC. Sarcopenia is associated with recent recurrence after hepatectomy for hepatitis B-related HCC. A nutritional status-based prediction model is first established for postoperative recurrence of hepatitis B-related HCC, which is superior to other models and contributes to prognosis prediction.

Identification and validation of a novel Parkinson-Glioma feature gene signature in glioma and Parkinson's disease.

The prognosis for glioma is generally poor, and the 5-year survival rate for patients with this disease has not shown significant improvement over the past few decades. Parkinson's disease (PD) is a prevalent movement disorder, ranking as the second most common neurodegenerative disease after Alzheimer's disease. Although Parkinson's disease and glioma are distinct diseases, they may share certain underlying biological pathways that contribute to their development. This study aims to investigate the involvement of genes associated with Parkinson's disease in the development and prognosis of glioma. We obtained datasets from the TCGA, CGGA, and GEO databases, which included RNA sequencing data and clinical information of glioma and Parkinson's patients. Eight machine learning algorithms were used to identify Parkinson-Glioma feature genes (PGFGs). PGFGs associated with glioma prognosis were identified through univariate Cox analysis. A risk signature was constructed based on PGFGs using Cox regression analysis and the Least Absolute Shrinkage and Selection Operator (LASSO) method. We subsequently validated its predictive ability using various methods, including ROC curves, calibration curves, KM survival analysis, C-index, DCA, independent prognostic analysis, and stratified analysis. To validate the reproducibility of the results, similar work was performed on three external test datasets. Additionally, a meta-analysis was employed to observe the heterogeneity and consistency of the signature across different datasets. We also compared the differences in genomic variations, functional enrichment, immune infiltration, and drug sensitivity analysis based on risk scores. This exploration aimed to uncover potential mechanisms of glioma occurrence and prognosis. We identified 30 PGFGs, of which 25 were found to be significantly associated with glioma survival. The prognostic signature, consisting of 19 genes, demonstrated excellent predictive performance for 1-, 2-, and 3-year overall survival (OS) of glioma. The signature emerged as an independent prognostic factor for glioma overall survival (OS), surpassing the predictive performance of traditional clinical variables. Notably, we observed differences in the tumor microenvironment (TME), levels of immune cell infiltration, immune gene expression, and drug resistance analysis among distinct risk groups. These findings may have significant implications for the clinical treatment of glioma patients. The expression of genes related to Parkinson's disease is closely associated with the immune status and prognosis of glioma patients, potentially regulating glioma pathogenesis through multiple mechanisms. The interaction between genes associated with Parkinson's disease and the immune system during glioma development provides novel insights into the molecular mechanisms and targeted therapies for glioma.

Development of interpretable machine learning models associated with environmental chemicals to predict all-cause and specific-cause mortality：A longitudinal study based on NHANES

Limited information is available on potential predictive value of environmental chemicals for mortality. Our study aimed to investigate the associations between 43 of 8 classes representative environmental chemicals in serum/urine and mortality, and further develop the interpretable machine learning models associated with environmental chemicals to predict mortality. A total of 1602 participants were included from the National Health and Nutrition Examination Survey (NHANES). During 154,646 person-months of follow-up, 127 deaths occurred. We found that machine learning showed promise in predicting mortality. CoxPH was selected as the optimal model for predicting all-cause mortality with time-dependent AUROC of 0.953 (95%CI: 0.951–0.955). Coxnet was the best model for predicting cardiovascular disease (CVD) and cancer mortality with time-dependent AUROCs of 0.935 (95%CI: 0.933–0.936) and 0.850 (95%CI: 0.844–0.857). Based on clinical variables, adding environmental chemicals could enhance the predictive ability of cancer mortality (P < 0.05). Some environmental chemicals contributed more to the models than traditional clinical variables. Combined the results of association and prediction models by interpretable machine learning analyses, we found urinary methyl paraben (MP) and urinary 2-napthol (2-NAP) were negatively associated with all-cause mortality, while serum cadmium (Cd) was positively associated with all-cause mortality. Urinary bisphenol A (BPA) was positively associated with CVD mortality.

Development, validation, and comparative analysis of a simple clinical and laboratory-based risk score system for predicting and stratifying moderate-to-severe AKI after cardiac surgery

Abstract Background Cardiac Surgery-Associated Acute Kidney Injury (CSA-AKI) is prevalent and detrimental following cardiac surgery, without effective prevention. Early prediction and stratification are critical in informing appropriate care. Recent studies highlighted the predictive value of some routine laboratory markers in addition to traditional clinical variables. However, existing models suffer from complexity and practical difficulties in implementation. Purpose We aim to develop a high-performance preoperative risk score system for predicting moderate-to-severe CSA-AKI, while preserving its simplicity and utility through the integration of the most predictive and routinely accessible clinical and laboratory variables. Methods A total of 14 303 patients undergoing coronary artery bypass grafting surgery at a single institution, with comprehensive perioperative data, were included. Cohort 1 (N=9 416, 2013-2017) and cohort 2 (N=4 887, 2018-2019) were used to develop and validate a risk score system for predicting moderate-to-severe CSA-AKI, respectively, according to the Kidney Disease: Improving Global Outcomes (KDIGO) guidelines. Bootstrapped stepwise regression was employed to select the robust candidate variables for a logistic regression model (i.e., the full model), which was then simplified to a more parsimonious model. Model performance was evaluated and compared to several established models. Results The overall incidence of moderate-to-severe CSA-AKI was 3.5% in the entire cohort. Two preoperative risk scores were developed: the simple 6-variable ABC2-Surgery2 score (age, a biomarker of NT-proBNP, two clinical status variables of hypertension and preoperative critical state, and two surgery-related variables of combined surgery and on-pump surgery), and the complete 10-variable AB2C3-Surgery4 score (ABC2-Surgery2 plus an additional biomarker of blood urea nitrogen, a clinical status variable of Canadian Cardiovascular Society angina class, and two surgery-related variables of urgent surgery and previous surgery). In the validation cohort, the simple score (area under the curve, AUC 0.765) outperformed the previously established UK-AKI model (AUC 0.720), Mehta score (AUC 0.700), and Ng score (AUC 0.697), while statistically similar to the most complex 19-variable Cleveland Clinic Score (AUC 0.725). The complete score (AUC 0.777) was superior to all four models. The current score system also effectively stratified CSA-AKI with respect to requirements for vasoactive support (measured by cumulative vasoactive-inotropic score), intravenous diuretics, and renal replacement therapy, as well as in-hospital and long-term mortality. Conclusion A simple risk score system incorporating routine clinical and laboratory variables was developed to predict and stratify moderate-to-severe CSA-AKI and outperformed previous complex models. Further external validation is currently underway for generalizability.

Identification of a coagulation-related signature correlated with immune infiltration and their prognostic implications in lung adenocarcinoma.

Lung adenocarcinoma (LUAD) is a fatal form of lung cancer with a poor prognosis. Coagulation system had been confirmed closely related to tumor progression and the hypercoagulable state encouraged the immune infiltration and development of tumor cells, leading to a poor prognosis in cancer patients. However, the use of the coagulation-related genes (CRGs) for prognosis in LUAD has yet to be determined. In this study, we constructed an immune-related signature (CRRS) and identified a potential coagulation-related biomarker (P2RX1). We obtained a total of 209 CRGs based on two coagulation-related KEGG pathways, then developed the CRRS signature by using the TCGA-LUAD RNA-seq data via the procedure of LASSO-Cox regression, stepwise-Cox regression, univariate and multivariate Cox regression. Grouped by the CRRS, Kaplan-Meier survival curves and receiver operating characteristic curves were drawn for the training and validation sets, respectively. In addition, single-sample gene set enrichment analysis was exploited to explore immune infiltration level. Moreover, immunophenotypes and immunotherapy grouped by CRRS were further analyzed. We developed an immune-related signature (CRRS) composed of COL1A2, F2, PLAUR, C4BPA, and P2RX1 in LUAD. CRRS was an independent risk factor for overall survival and displayed stable and powerful performance. Additionally, CRRS possessed distinctly superior accuracy than traditional clinical variables and molecular features. Functional analysis indicated that the differentially high expressed genes in the low-risk group significantly enriched in T cell and B cell receptor signaling pathways. The low-risk group was sensitive to anti-PD-1/PD-L1 immunotherapy and displayed abundant immune infiltration and immune checkpoint gene expression. Finally, we identified an independent prognostic gene P2RX1. Low expression of P2RX1 associated with poor overall survival and decreased immune infiltration. Our study revealed a significant correlation between CRRS and immune infiltration. CRRS could serve as a promising tool to improve the clinical outcomes for individual LUAD patients.

Machine Learning Improves Risk Stratification in Myelodysplastic Neoplasms: An Analysis of the Spanish Group of Myelodysplastic Syndromes.

Myelodysplastic neoplasms (MDS) are a heterogeneous group of hematological stem cell disorders characterized by dysplasia, cytopenias, and increased risk of acute leukemia. As prognosis differs widely between patients, and treatment options vary from observation to allogeneic stem cell transplantation, accurate and precise disease risk prognostication is critical for decision making. With this aim, we retrieved registry data from MDS patients from 90 Spanish institutions. A total of 7202 patients were included, which were divided into a training (80%) and a test (20%) set. A machine learning technique (random survival forests) was used to model overall survival (OS) and leukemia-free survival (LFS). The optimal model was based on 8 variables (age, gender, hemoglobin, leukocyte count, platelet count, neutrophil percentage, bone marrow blast, and cytogenetic risk group). This model achieved high accuracy in predicting OS (c-indexes; 0.759 and 0.776) and LFS (c-indexes; 0.812 and 0.845). Importantly, the model was superior to the revised International Prognostic Scoring System (IPSS-R) and the age-adjusted IPSS-R. This difference persisted in different age ranges and in all evaluated disease subgroups. Finally, we validated our results in an external cohort, confirming the superiority of the Artificial Intelligence Prognostic Scoring System for MDS (AIPSS-MDS) over the IPSS-R, and achieving a similar performance as the molecular IPSS. In conclusion, the AIPSS-MDS score is a new prognostic model based exclusively on traditional clinical, hematological, and cytogenetic variables. AIPSS-MDS has a high prognostic accuracy in predicting survival in MDS patients, outperforming other well-established risk-scoring systems.

Characterizing the key genes of COVID-19 that regulate tumor immune microenvironment and prognosis in hepatocellular carcinoma.

Hepatocellular carcinoma (HCC), a highly heterogeneous malignant tumor associated with a poor prognosis, is a common cause of cancer-related deaths worldwide, with a limited survival benefit for patients despite ongoing therapeutic breakthroughs. Coronavirus disease 2019 (COVID-19), a severe infectious disease caused by severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2), is a global pandemic and a serious threat to human health. The increased susceptibility to SARS-CoV-2 infection and a poor prognosis in patients with cancer necessitate the exploration of the potential link between the two. No studies have investigated the relationship of COVID-19 genes with the prognosis and tumor development in patients with HCC. We screened prognosis-related COVID-19 genes in HCC, performed molecular typing, developed a stable and reliable COVID-19 genes signature for predicting survival, characterized the immune microenvironment in HCC patients, and explored new molecular therapeutic targets. Datasets of HCC patients, including RNA sequencing data and clinical information, were obtained from The Cancer Genome Atlas (TCGA), International Cancer Genome Consortium (ICGC), and Gene Expression Omnibus (GEO) databases. Prognosis-related COVID-19 genes were identified by univariate Cox analysis. Molecular typing of HCC was performed using the consensus non-negative matrix factorization method (cNMF), followed by the analysis of survival, tumor microenvironment, and pathway enrichment for each subtype. Prognostic signatures were constructed using LASSO-Cox regression models, and receiver operating characteristic (ROC) curves were used to validate the predictive performance of the signature. The same approach was used for the test and external validation sets. Seven software packages were applied to determine the abundance of immune infiltration in HCC patients and investigate its relationship with the risk scores. Gene set enrichment analysis (GSEA) was used to explore the potential mechanisms by which the COVID-19 genes affect hepatocarcinogenesis and prognosis. Three types of machine learning methods were combined to identify the most critical genes in the signature and localize their expression at the single cell level. We identified 53 prognosis-related COVID-19 genes and classified HCC into two molecular subtypes (C1, C2) by using the NMF method. The prognosis of C2 was significantly better than that of C1, and the two subtypes differed remarkably in terms of the tumor immune microenvironment and biological functions. The 17 COVID-19 genes were screened using the LASSO regression method to develop a 17 COVID-19 genes signature, which demonstrated a good predictive performance for 1-, 2- and 3-year OS of patients with HCC. The risk score as an independent prognostic factor for HCC has better predictive accuracy than traditional clinical variables. Patients in the TCGA cohort were categorized by risk score into the high- and low-risk groups, with the high-risk group mainly enriched in the immune modulation-related pathways and the low-risk group mainly enriched in the metabolism-related pathways, suggesting that the COVID-19 genes may affect disease progression and prognosis by regulating the tumor immune microenvironment and metabolism in HCC. NOL10 was identified as the most critical gene in the signature and hypothesized to be a potential therapeutic target for HCC. Objectively, the COVID-19 genes signature developed in this study, as an independent prognostic factor in HCC patients, is closely associated with the prognosis and tumor immune microenvironment of HCC patients and indicates that they may regulate the development of HCC in multiple ways, providing us with new perspectives for understanding the molecular mechanisms of HCC and finding effective therapeutic targets.

Multi-center validation of an immune-related lncRNA signature for predicting survival and immune status of patients with renal cell carcinoma: an integrating machine learning-derived study.

Long noncoding RNAs (lncRNAs) have been reported to play an important role in tumor immune modification. Nonetheless, the clinical implication of immune-associated lncRNAs in renal cell carcinoma (RCC) remains to be further explored. 76 combinations of machine learning algorithms were integrated to develop and validate a machine learning-derived immune-related lncRNA signature (MDILS) in five independent cohorts (n = 801). We collected 28 published signatures and collated clinical variables for comparison with MDILS to verify its efficacy. Subsequently, molecular mechanisms, immune status, mutation landscape, and pharmacological profile were further investigated in different stratified patients. Patients with high MDILS displayed worse overall survival than those with low MDILS. The MDILS could independently predict overall survival and convey robust performance across five cohorts. MDILS has a significantly better performance compared with traditional clinical variables and 28 published signatures. Patients with low MDILS exhibited more abundant immune infiltration and higher potency of immunotherapeutic response, while patients with high MDILS might be more sensitive to multiple chemotherapeutic drugs (e.g., sunitinib and axitinib). MDILS is a robust and promising tool to facilitate clinical decision-making and precision treatment of RCC.

Impact of sociodemographic disadvantage on neurobehavioral outcomes in children with newly diagnosed seizures and their unaffected siblings over 36 months.

This study was undertaken to determine the short-term and longer term impact of sociodemographic disadvantage on the emotional-behavioral status of youths with new onset epilepsy and their unaffected siblings at the time of diagnosis and the subsequent 3 years. Three hundred twelve youths with newly diagnosed epilepsies and 223 unaffected siblings, aged 6-16 years, were independently assessed regarding their emotional and behavioral status by their parents and teachers at baseline, and at 18 at 36 months later; youths with seizures also completed self-report measures of depression, anxiety, and hostility at those three time points. A sociodemographic disadvantage score was computed for each family (children with newly diagnosed seizures and their siblings), and families were separated into four categories from most disadvantaged to least disadvantaged. In both children and siblings, the least disadvantaged group exhibited the lowest level of neurobehavioral problems, whereas the most disadvantaged group showed a higher level of neurobehavioral problems across all the same behavior metrics. Findings remained stable and significant across all informants (parent, teacher, child) and across all time periods (throughout the 3-year period). Furthermore, both corrected and uncorrected linear regression analyses indicated that disadvantage was a more constant and stable predictor of behavioral and emotional problems over time compared to clinical seizure characteristics and abnormalities in magnetic resonance imaging and electroencephalographic testing. Sociodemographic disadvantage bears a strong relationship to youths with emotional and behavioral problems both at the time of diagnosis as well as prospectively. The relationship is robust and reflected in reports from multiple informants (parent, teacher, child self-report), evident in siblings as well, and possibly more explanatory than traditional clinical seizure variables. Future studies will be needed to determine whether this disadvantage factor is modifiable with early intervention.

Lung cancer multi-omics digital human avatars for integrating precision medicine into clinical practice: the LANTERN study

BackgroundThe current management of lung cancer patients has reached a high level of complexity. Indeed, besides the traditional clinical variables (e.g., age, sex, TNM stage), new omics data have recently been introduced in clinical practice, thereby making more complex the decision-making process. With the advent of Artificial intelligence (AI) techniques, various omics datasets may be used to create more accurate predictive models paving the way for a better care in lung cancer patients.MethodsThe LANTERN study is a multi-center observational clinical trial involving a multidisciplinary consortium of five institutions from different European countries. The aim of this trial is to develop accurate several predictive models for lung cancer patients, through the creation of Digital Human Avatars (DHA), defined as digital representations of patients using various omics-based variables and integrating well-established clinical factors with genomic data, quantitative imaging data etc. A total of 600 lung cancer patients will be prospectively enrolled by the recruiting centers and multi-omics data will be collected. Data will then be modelled and parameterized in an experimental context of cutting-edge big data analysis. All data variables will be recorded according to a shared common ontology based on variable-specific domains in order to enhance their direct actionability. An exploratory analysis will then initiate the biomarker identification process. The second phase of the project will focus on creating multiple multivariate models trained though advanced machine learning (ML) and AI techniques for the specific areas of interest. Finally, the developed models will be validated in order to test their robustness, transferability and generalizability, leading to the development of the DHA. All the potential clinical and scientific stakeholders will be involved in the DHA development process. The main goals aim of LANTERN project are: i) To develop predictive models for lung cancer diagnosis and histological characterization; (ii) to set up personalized predictive models for individual-specific treatments; iii) to enable feedback data loops for preventive healthcare strategies and quality of life management.DiscussionThe LANTERN project will develop a predictive platform based on integration of multi-omics data. This will enhance the generation of important and valuable information assets, in order to identify new biomarkers that can be used for early detection, improved tumor diagnosis and personalization of treatment protocols.Ethics Committee approval number5420 − 0002485/23 from Fondazione Policlinico Universitario Agostino Gemelli IRCCS – Università Cattolica del Sacro Cuore Ethics Committee.Trial registrationclinicaltrial.gov - NCT05802771.

Respiratory effort during sleep and the rate of prevalent type 2 diabetes in obstructive sleep apnoea.

To determine the association between total sleep time (TST) spent in increased respiratory effort (RE) and the prevalence of type 2 diabetes in a large cohort of individuals with suspected obstructive sleep apnoea (OSA) referred for in-laboratory polysomnography (PSG). We conducted a retrospective cross-sectional study using the clinical data of 1128 patients. Non-invasive measurements of RE were derived from the sleep mandibular jaw movements (MJM) bio-signal. An explainable machine-learning model was built to predict prevalent type 2 diabetes from clinical data, standard PSG indices, and MJM-derived parameters (including the proportion of TST spent with increased respiratory effort [REMOV [%TST]). Original data were randomly assigned to training (n = 853) and validation (n = 275) subsets. The classification model based on 18 input features including REMOV showed good performance for predicting prevalent type 2 diabetes (sensitivity = 0.81, specificity = 0.89). Post hoc interpretation using the Shapley additive explanation method found that a high value of REMOV was the most important risk factor associated with type 2 diabetes after traditional clinical variables (age, sex, body mass index), and ahead of standard PSG metrics including the apnoea-hypopnea and oxygen desaturation indices. These findings show for the first time that the proportion of sleep time spent in increased RE (assessed through MJM measurements) is an important predictor of the association with type 2 diabetes in individuals with OSA.

Bulk and single-cell RNA-sequencing analyses along with abundant machine learning methods identify a novel monocyte signature in SKCM.

Global patterns of immune cell communications in the immune microenvironment of skin cutaneous melanoma (SKCM) haven't been well understood. Here we recognized signaling roles of immune cell populations and main contributive signals. We explored how multiple immune cells and signal paths coordinate with each other and established a prognosis signature based on the key specific biomarkers with cellular communication. The single-cell RNA sequencing (scRNA-seq) dataset was downloaded from the Gene Expression Omnibus (GEO) database, in which various immune cells were extracted and re-annotated according to cell markers defined in the original study to identify their specific signs. We computed immune-cell communication networks by calculating the linking number or summarizing the communication probability to visualize the cross-talk tendency in different immune cells. Combining abundant analyses of communication networks and identifications of communication modes, all networks were quantitatively characterized and compared. Based on the bulk RNA sequencing data, we trained specific markers of hub communication cells through integration programs of machine learning to develop new immune-related prognostic combinations. An eight-gene monocyte-related signature (MRS) has been built, confirmed as an independent risk factor for disease-specific survival (DSS). MRS has great predictive values in progression free survival (PFS) and possesses better accuracy than traditional clinical variables and molecular features. The low-risk group has better immune functions, infiltrated with more lymphocytes and M1 macrophages, with higher expressions of HLA, immune checkpoints, chemokines and costimulatory molecules. The pathway analysis based on seven databases confirms the biological uniqueness of the two risk groups. Additionally, the regulon activity profiles of 18 transcription factors highlight possible differential regulatory patterns between the two risk groups, suggesting epigenetic event-driven transcriptional networks may be an important distinction. MRS has been identified as a powerful tool to benefit SKCM patients. Moreover, the IFITM3 gene has been identified as the key gene, validated to express highly at the protein level via the immunohistochemical assay in SKCM. MRS is accurate and specific in evaluating SKCM patients' clinical outcomes. IFITM3 is a potential biomarker. Moreover, they are promising to improve the prognosis of SKCM patients.

Integrated analysis of single-cell and bulk RNA sequencing identifies a signature based on macrophage marker genes involved in prostate cancer prognosis and treatment responsiveness

In the tumor microenvironment, tumor-associated macrophages (TAMs) interact with cancer cells and contribute to the progression of solid tumors. Nonetheless, the clinical significance of TAM-related biomarkers in prostate cancer (PCa) is largely unexplored. The present study aimed to construct a macrophage-related signature (MRS) for predicting PCa patient prognosis based on macrophage marker genes. Six cohorts comprising 1056 PCa patients with RNA-Seq and follow-up data were enrolled. Based on macrophage marker genes identified by single-cell RNA-sequencing (scRNA-seq) analysis, univariate analysis, least absolute shrinkage and selection operator (Lasso)-Cox regression, and machine learning procedures were performed to derive a consensus MRS. Receiver operating characteristic curve (ROC), concordance index, and decision curve analyses were used to confirm the predictive capacity of the MRS. The predictive performance of the MRS for recurrence-free survival (RFS) was stable and robust, and the MRS outperformed traditional clinical variables. Furthermore, high-MRS-score patients presented abundant macrophage infiltration and high-expression levels of immune checkpoints (CTLA4, HAVCR2, and CD86). The frequency of mutations was relatively high in the high-MRS-score subgroup. However, the low-MRS-score patients had a better response to immune checkpoint blockade (ICB) and leuprolide-based adjuvant chemotherapy. Notably, abnormal ATF3 expression may be associated with docetaxel and cabazitaxel resistance in PCa cells, T stage, and the Gleason score. In this study, a novel MRS was first developed and validated to accurately predict patient survival outcomes, evaluate immune characteristics, infer therapeutic benefits, and provide an auxiliary tool for personalized therapy.

Illustrating the biological functions and diagnostic value of transmembrane protein family members in glioma.

It is well-established that patients with glioma have a poor prognosis. Although the past few decades have witnessed unprecedented medical advances, the 5-year survival remains dismally low. This study aims to investigate the role of transmembrane protein-related genes in the development and prognosis of glioma and provide new insights into the pathogenesis of the disease. The datasets of glioma patients, including RNA sequencing data and relative clinical information, were obtained from The Cancer Genome Atlas (TCGA), Chinese Glioma Genome Atlas (CGGA) and Gene Expression Omnibus (GEO) databases. Prognostic transmembrane protein-related genes were identified by univariate Cox analysis. New disease subtypes were recognized based on the consensus clustering method, and their biological uniqueness was verified via various algorithms. The prognosis signature was constructed using the LASSO-Cox regression model, and its predictive power was validated in external datasets by receiver operating characteristic (ROC) curve analysis. An independent prognostic analysis was conducted to evaluate whether the signature could be considered a prognostic factor independent of other variables. A nomogram was constructed in conjunction with traditional clinical variables. The concordance index (C-index) and Decision Curve Analysis (DCA) were used to assess the net clinical benefit of the signature over traditional clinical variables. Seven different softwares were used to compare the differences in immune infiltration between the high- and low-risk groups to explore potential mechanisms of glioma development and prognosis. Hub genes were found using the random forest method, and their expression was based on multiple single-cell datasets. Four molecular subtypes were identified, among which the C1 group had the worst prognosis. Principal Component Analysis (PCA) results and heatmaps indicated that prognosis-related transmembrane protein genes exhibited differential expression in all four groups. Besides, the microenvironment of the four groups exhibited significant heterogeneity. The 6 gene-based signatures could predict the 1-, 2-, and 3-year overall survival (OS) of glioma patients. The signature could be used as an independent prognosis factor of glioma OS and was superior to traditional clinical variables. More immune cells were infiltrated in the high-risk group, suggesting immune escape. According to our signature, many genes were associated with the content of immune cells, which revealed that transmembrane protein-related genes might influence the development and prognosis of glioma by regulating the immune microenvironment. TMEM158 was identified as the most important gene using the random forest method. The single-cell datasets consistently showed that TMEM158 was expressed in multiple malignant cells. The expression of transmembrane protein-related genes is closely related to the immune status and prognosis of glioma patients by regulating tumor progression in various ways. The interaction between transmembrane protein-related genes and immunity during glioma development lays the groundwork for future studies on the molecular mechanism and targeted therapy of glioma.

Systematic integration of machine learning algorithms to develop immune escape-related signatures to improve clinical outcomes in lung adenocarcinoma patients.

Immune escape has recently emerged as one of the barriers to the efficacy of immunotherapy in lung adenocarcinoma (LUAD). However, the clinical significance and function of immune escape markers in LUAD have largely not been clarified. In this study, we constructed a stable and accurate immune escape score (IERS) by systematically integrating 10 machine learning algorithms. We further investigated the clinical significance, functional status, TME interactions, and genomic alterations of different IERS subtypes to explore potential mechanisms. In addition, we validated the most important variable in the model through cellular experiments. The IERS is an independent risk factor for overall survival, superior to traditional clinical variables and published molecular signatures. IERS-based risk stratification can be well applied to LUAD patients. In addition, high IERS is associated with stronger tumor proliferation and immunosuppression. Low IERS exhibited abundant lymphocyte infiltration and active immune activity. Finally, high IERS is more sensitive to first-line chemotherapy for LUAD, while low IERS is more sensitive to immunotherapy. In conclusion, IERS may serve as a promising clinical tool to improve risk stratification and clinical management of individual LUAD patients and may enhance the understanding of immune escape.

Abstract WMP27: Augmenting Early Prediction Of Post-Rehabilitation Ambulation Ability And Risk Of Falling Status For Recovering Stroke Patients Using Wearable Sensors And Machine Learning

Introduction: Inertial measurement units (IMU) can capture objective biomarkers of recovery during everyday activity paving the way to early prognosis and personalized therapy in post-stroke rehabilitation. In this study, we evaluated the performance of IMU data incorporated into machine learning models to predict discharge abilities compared to models based on traditional clinical variables. Methods: 32 subacute stroke patients admitted to inpatient rehabilitation performed clinical tests while wearing IMU sensors placed on the pelvis and both unaffected and affected-side shanks (US, AS). Variables collected were patient information (PI), clinician-scored functional assessments (FA), signal-processed IMU data during the 10-Meter Walk Test (IMU 10MWT ) and the Berg-Balance Scale (IMU BBS ). Patients were identified as household or community ambulators (Amb), and with high or normal risk of fall (RoF) based on discharge functional scores. A class-weighted L1-penalized logistic regression model was trained using nested leave-one-out cross-validation on admission data to predict discharge Amb and RoF statuses. The impact of sensor data on model performance was assessed on three feature sets: PI+FA, PI+IMU 10MWT/BBS , PI+FA+IMU 10MWT/BBS . Evaluation metrics included: weighted F1 score (WF1), accuracy, log-loss, and feature importance. Results: The PI+FA+IMU BBS , and both the PI+IMU 10MWT and PI+FA+IMU 10MWT models, outperformed the PI + FA benchmark model for RoF and Amb prediction, respectively, across all metrics (Figure 1). US gyroscopic and AS/US acceleration were relevant for Amb prediction, while the admission BBS score and pelvic acceleration were important to RoF prediction. Conclusions: Incorporation of simple IMU data from admission can improve discharge functional predictions over a model using PI and FA. Early, accurate predictions of post-stroke recovery could facilitate more personalized and efficient rehabilitation strategies.