Clinical Prediction Model Research Articles

Clinical prediction model for bacterial co-infection in hospitalized COVID-19 patients during four waves of the pandemic.

Estimates of bacterial coinfection in COVID-19 patients are highly variable and depend on many factors. Patients with severe or critical COVID-19 requiring intensive care unit admission have the highest risk of infection-related complications and death. Thus, the study of the incidence and risk factors for bacterial coinfection in this population is of special interest and may help guide empiric antibiotic therapy and avoid unnecessary antimicrobial treatment. The prediction model based on clinical criteria and simple laboratory tests may be a useful tool to predict bacterial co-infection in patients hospitalized with severe COVID-19.

Codesigning a Clinical Prediction Model for Aboriginal Perinatal Mental Health Using Glassbox AI and Aboriginal Wisdom and Lived Experience.

Perinatal mental health is vital for mothers, infants, and families. Aboriginal mothers, despite their strengths, face greater mental health disparities due to colonisation and trauma. Traditional screening methods lack cultural sensitivity. The Baby Coming You Ready (BCYR) program offers a culturally sensitive assessment with promising pilot results. To support health professionals, an AI solution using the Explainable Boosting Machine (EBM) is proposed, trained with Aboriginal lived experiences. This model identifies maternal protective and risk factors, offering interpretable predictions for holistic culturally sensitive care.

Mitochondrial-related genes as prognostic and metastatic markers in breast cancer: insights from comprehensive analysis and clinical models.

Breast cancer (BC) constitutes a significant peril to global women's health. Contemporary research progressively suggests that mitochondrial dysfunction plays a pivotal role in both the inception and advancement of BC. However, investigations delving into the correlation between mitochondrial-related genes (MRGs) and the prognosis and metastasis of BC are still infrequent. Utilizing data from the TCGA database, we employed the "limma" R package for differential expression analysis. Subsequently, both univariate and multivariate Cox regression analyses were executed, alongside LASSO Cox regression analysis, to pinpoint prognostic MRGs and to further develop the prognostic model. External validation (GSE88770 merged GSE425680) and internal validation were further conducted. Our investigation delved into a broad spectrum of analyses that included functional enrichment, metabolic and immune characteristics, immunotherapy response prediction, intratumor heterogeneity (ITH), mutation, tumor mutational burden (TMB), microsatellite instability (MSI), cellular stemness, single-cell, and drug sensitivity analysis. We validated the protein and mRNA expressions of prognostic MRGs in tissues and cell lines through immunohistochemistry and qRT-PCR. Moreover, leveraging the GSE102484 dataset, we conducted differential gene expression analysis to identify MRGs related to metastasis, subsequently developing metastasis models via 10 distinct machine-learning algorithms and then selecting the best-performing model. The division between training and validation cohorts was set at 70% and 30%, respectively. A prognostic model was constructed by 9 prognostic MRGs, which were DCTPP1, FEZ1, KMO, NME3, CCR7, ISOC2, STAR, COMTD1, and ESR2. Patients within the high-risk group experienced more adverse outcomes than their counterparts in the low-risk group. The ROC curves and constructed nomogram showed that the model exhibited an excellent ability to predict overall survival (OS) for patients and the risk score was identified as an independent prognostic factor. The functional enrichment analysis showed a strong correlation between metabolic progression and MRGs. Additional research revealed that the discrepancies in outcomes between the two risk categories may be attributed to a variety of metabolic and immune characteristics, as well as differences in intratumor heterogeneity (ITH), tumor mutational burden (TMB), and cancer stemness indices. ITH, TIDE, and IPS analyses suggested that patients possessing a low-risk score may exhibit enhanced responsiveness to immunotherapy. Additionally, distant metastasis models were established by PDK4, NRF1, DCAF8, CHPT1, MARS2 and NAMPT. Among these, the XGBoost model showed the best predicting ability. In conclusion, MRGs significantly influence the prognosis and metastasis of BC. The development of dual clinical prediction models offers crucial insights for tailored and precise therapeutic strategies, and paves the way for exploring new avenues in understanding the pathogenesis of BC.

Development and validation of a clinical prediction model for osteonecrosis of the jaw in patients receiving zoledronic acid using FAERS and canadian databases.

Osteonecrosis of the jaw (ONJ) stands as a severe complication linked to the use of bisphosphonates, particularly zoledronic acid, which is widely prescribed for managing conditions like osteoporosis and bone metastasis. This study is geared towards the development and validation of a clinical prediction model for ONJ in patients undergoing zoledronic acid treatment. We harnessed data from the FDA Adverse Event Reporting System (FAERS) as our training dataset, while the Canada Vigilance Adverse Reaction (CVAR) database served as the testing dataset. The study encompassed patients treated with zoledronic acid and subsequently diagnosed with ONJ. We analysed a range of predictive factors, including breast cancer, bone metastasis, osteoporosis, vitamin D and calcium levels, comorbidities, the number of concomitant medications, dosage, age, weight, and gender. Logistic regression and nomogram analysis were the chosen methodologies for constructing the predictive model. To evaluate the model's performance, we utilized receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). The study encompassed a total of 2,126 patients in the training cohort, 911 patients in the internal test cohort from the FAERS database, and 121 patients in the external test cohort from the CVAR database. Notable predictors for ONJ included bone metastasis (OR: 1.65, 95% CI: 1.22-2.24), osteoporosis (OR: 0.33, 95% CI: 0.21-0.52), the number of concomitant medications (OR: 1.07, 95% CI: 1.05-1.09), and the dosage of zoledronic acid (OR: 1.24, 95% CI: 1.10-1.39). The nomogram exhibited robust discriminatory power, evidenced by an area under the curve (AUC) of 0.77 in the training cohort, 0.76 in the internal test cohort, and 0.90 in the external test cohort. Calibration plots demonstrated a strong alignment between observed and predicted probabilities. Furthermore, DCA highlighted the prediction model's significant net benefit across various threshold probabilities. By leveraging data from both the FAERS and Canadian databases, this study has successfully developed and validated a clinical prediction model for ONJ in patients receiving zoledronic acid. This model stands as a valuable tool for clinicians, enabling them to pinpoint high-risk patients and make evidence-based treatment decisions to minimize the risk of ONJ.

Improve clinical feature-based bladder cancer survival prediction models through integration with gene expression profiles and machine learning techniques

BackgroundBladder cancer (BCa), one of the most common cancers worldwide, is characterized by high rates of recurrence, progression, and mortality. Machine learning algorithms offer promising advancements in enhancing predictive models. This study aims to develop robust machine learning models for predicting BCa survival using clinical and gene expression data. MethodsClinical data from BCa patients were obtained from the Surveillance, Epidemiology, and End Results database. Cox proportional hazards regression models assessed the association between clinical variables and overall survival. Machine learning algorithms, including logistic regression, random forest, XGBoost, decision tree, and LightGBM, were employed to predict survival at 1, 3, and 5 years. The TAGO database, combined with the data from The Cancer Genome Atlas and four databases from the Gene Expression Omnibus, which have available genomic data and clinical data, were selected. Gene expression data were transformed into gene sets data, and the performance of models based on clinical data and gene sets data and their combination were compared. Furthermore, the impact of model-derived scores on overall survival was evaluated. ResultsAmong 138,741 BCa patients with available clinical data, key independent predictors of survival included age, race, marital status, surgery, chemotherapy, radiation, and TNM stages. Clinical data machine learning (CML) models used these clinical predictors to achieve AUC values of 0.860, 0.821, and 0.804 in the testing sets for predicting survival at 1, 3, and 5 years, respectively. In the TAGO database, which has 863 patients with clinical and genomic data, the integrated clinical and gene expression machine learning model (IML) outperformed the CML and gene expression machine learning (GML) models in survival prediction. Patients with higher IML and GML model scores exhibited poorer survival outcomes. ConclusionsThis study successfully identifies key clinical and genomic predictors, a significant step forward in BCa research. The development of predictive models for BCa survival underscores the potential of integrated data approaches in improving BCa management and treatment strategies.

Machine learning-enabled mental health risk prediction for youths with stressful life events: A modelling study

BackgroundYouths face significant mental health challenges exacerbated by stressful life events, particularly in the context of the COVID-19 pandemic. Immature coping strategies can worsen mental health outcomes. MethodsThis study utilised a two-wave cross-sectional survey design with data collected from Chinese youth aged 14–25 years. Wave 1 (N = 3038) and Wave 2 (N = 539) datasets were used for model development and external validation, respectively. Twenty-five features, encompassing dimensions related to demographic information, stressful life events, social support, coping strategies, and emotional intelligence, were input into the model to predict the mental health status of youth, which was considered their coping outcome. Shapley additive explanation (SHAP) was used to determine the importance of each risk factor in the feature selection. The intersection of top 10 features identified by random forest and XGBoost were considered the most influential predictors of mental health during the feature selection process, and was then taken as the final set of features for model development. Machine learning models, including logistic regression, AdaBoost, and a backpropagation neural network (BPNN), were trained to predict the outcomes. The optimum model was selected according to the performance in both internal and external validation. ResultsThis study identified six key features that were significantly associated with mental health outcomes: punishment, adaptation issues, self-regulation of emotions, learning pressure, use of social support, and recognition of others' emotions. The BPNN model, optimized through feature selection methods like SHAP, demonstrated superior performance in internal validation (C-index [95 % CI] = 0.9120 [0.9111, 0.9129], F-score [95 % CI] = 0.8861 [0.8853, 0.8869]). Additionally, external validation showed the model had strong discrimination (C-index = 0.9749, F-score = 0.8442) and calibration (Brier score = 0.029) capabilities. LimitationsAlthough the clinical prediction model performed well, the study it still limited by self-reported data and representativeness of samples. Causal relationships need to be established to interpret the coping mechanism from multiple perspectives. Also, the limited data on minority groups may lead to algorithmic unfairness. ConclusionsMachine learning models effectively identified and predicted mental health outcomes among youths, with the SHAP+BPNN model showing promising clinical applicability. These findings emphasise the importance and effectiveness of targeted interventions with the help of clinical prediction model.

A clinical prediction model for distant metastases of pediatric neuroblastoma: an analysis based on the SEER database.

Patients with distant metastases from neuroblastoma (NB) usually have a poorer prognosis, and early diagnosis is essential to prevent distant metastases. The aim was to develop a machine-learning model for predicting the risk of distant metastasis in patients with neuroblastoma to aid clinical diagnosis and treatment decisions. We built a predictive model using data from the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2018 on 1,542 patients with neuroblastoma. Seven machine-learning methods were employed to forecast the likelihood of neuroblastoma distant metastases. Univariate and multivariate logistic regression analyses were used to identify independent risk factors for building machine learning models. Secondly, the subject operating characteristic area under the curve (AUC), Precision-Recall (PR) curves, decision curve analysis (DCA), and calibration curves were used to assess model performance. To further explain the optimal model, the Shapley summation interpretation method (SHAP) was applied. Ultimately, the best model was used to create an online calculator that estimates the likelihood of neuroblastoma distant metastases. The study included 1,542 patients with neuroblastoma, multifactorial logistic regression analysis showed that age, histology, tumor size, tumor grade, primary site, surgery, chemotherapy, and radiotherapy were independent risk factors for distant metastasis of neuroblastoma (P < 0.05). Logistic regression (LR) was found to be the optimal algorithm among the seven constructed, with the highest AUC values of 0.835 and 0.850 in the training and validation sets, respectively. Finally, we used the logistic regression model to build a network calculator for distant metastasis of neuroblastoma. The study developed and validated a machine learning model based on clinical and pathological information for predicting the risk of distant metastasis in patients with neuroblastoma, which may help physicians make clinical decisions.

Potential mechanistic linkages of Naoluotong granules on the remission of atherosclerosis by multidimensional analysis

BackgroundNaoluotong granules (NLTGs) are a medicinal formula derived from traditional Chinese medicine, which have been demonstrated to be effective in slowing down the progression of atherosclerosis (AS) through clinical practice and animal experiments. By means of multidimensional analysis, the relevant mechanism of NLTGs in delaying the progression of atherosclerosis was studied, which is conducive to its widespread adoption. Materials and methodsIn this study, data from network pharmacology and GEO database were comprehensively analysed to identify differentially expressed core cluster genes (DECCGs). Subsequently, multilevel analyses were applied to investigate the potential mechanistic linkages and causal associations of NLTGs in delaying atherosclerosis. ResultsEight DECCGs positively correlated with atherosclerosis risk were identified, with Polygonatum sibiricum (Huangjing), Hirudo nipponica (Shuizhi), and Ligusticum chuanxiong (Chuanxiong) as the core drug pairs. Senkyunone, Wallichilide, and Aurantiamide were the core components. The prediction model using principal components (PC) demonstrated high accuracy and clinical relevance. The mechanisms were strongly associated with the PI3K-Akt signaling pathway, as well as the polarization of Macrophages M0 and the balanced regulation of M1/M2 types. Ultimately, elevated expression of CTSB was causally associated with increased risk of cerebral atherosclerosis (OR = 1.313; 95 % CI = 1.024–1.685; P = 0.032). ConclusionsEmploying multidimensional analysis, we identified core pairs, components, and targets of NLTGs. Our multilevel analysis of DECCGs enabled the construction of a clinical prediction model, highlighting CTSB as a risk target for AS. Additionally, we unveiled NLTGs' mechanisms closely tied to the polarization and regulation of macrophage, facilitating subsequent research and application.

Unraveling the rapid progression of non-target lesions: risk factors and the therapeutic potential of PCSK9 inhibitors in post-PCI patients

BackgroundRapid progression of non-target lesions (NTLs) leads to a high incidence of NTL related cardiac events post-PCI, which accounting half of the recurrent cardiac events. It is important to identify the risk factors and establish an accurate clinical prediction model for the rapid progression of NTLs post-PCI. PCSK9 inhibitors lower LDL-c levels significantly, also show the anti-inflammation effect, and may have the potential to reduce the rapid progression of NTLs post-PCI. We tried to test this hypothesis and explore the potential mechanisms.MethodsThis retrospective study included 1250 patients who underwent the first PCI and underwent repeat coronary angiography for recurrence of chest pain within 24 months. General characteristics, laboratory tests and inflammatory factors(IL-10, IL-6, IL-8, IL-1β, sIL-2R, and TNF-α) were collected. Machine learning (LASSO regression) was mainly employed to select the important characteristic risk factors for the rapid progression of NTLs post-PCI and build prediction models. Finally, mediator analysis was employed to explore the potential mechanisms by which PCSK9 inhibitors reduce the rapid progression of NTLs post-PCI.ResultsThere were more diabetes, less beta-blockers and PCSK9 inhibitors application, higher HbA1c, LDL-c, ApoB, TG, TC, uric acid, hs-CRP, TNF-α, IL-6, IL-8, and sIL-2R in NTL progressed group. LDL-c, hs-CRP, IL-8, and sIL-2R were characteristic risk factors for the rapid progression of NTLs post-PCI, combining LDL-c, hs-CRP, IL-8, and sIL-2R builds the optimal model for predicting the rapid progression of NTLs post-PCI (AUC = 0.632). LDL-c had a clear and incomplete mediating effect (95% CI, mediating effect: 51.56%) in the reduction of the progression of NTLs by PCSK9 inhibitors, and there was a possible mediating effect of IL-8 (90% CI), and sIL-2R (90% CI).ConclusionsLDL-c, hs-CRP, IL-8, and sIL-2R may be the key characteristic risk factors for the rapid progression of NTLs post-PCI, and combining these parameters might predict the rapid progression of NTLs post-PCI. The application of PCSK9 inhibitors had a negative correlation with the rapid progression of NTLs. In addition to the significant LDL-c-lowering, PCSK9 inhibitors may reduce the rapid progression of NTLs by reducing local inflammation of plaque.Trial registrationChiCTR2200058529; Date of registration: 2022–04-10.

Are Psychiatric Nosologies Limiting the Success of Clinical Prediction Models?

This Viewpoint discusses the limitations of clinical prediction models in psychiatric research.

A Nomogram Based on Features of Ultrasonography and Contrast-Enhanced CT to Predict Vessels Encapsulating Tumor Clusters Pattern of Hepatocellular Carcinoma

ObjectiveThis study aimed to establish a clinical prediction model for vessels encapsulating tumor clusters (VETC) based on preoperative ultrasonography (US) and contrast-enhanced computed tomography (CECT) imaging in patients with hepatocellular carcinoma (HCC). MethodsData were retrospectively collected from 215 patients who underwent hepatectomy for solitary HCC lesions. They were divided into training and validation cohorts at a ratio of 6:4. Preoperative imaging features were extracted (seven from US and nine from CECT imaging) to explore their relationship with VETC. A VETC prediction model was constructed and graphically depicted as a nomogram. Its performance was evaluated via the receiver operating characteristic (ROC) curve, the calibration curve, and decision curve analysis (DCA). ResultsThe VETC incidence for all the lesions was 37.7%. The final variables included in the nomogram were “peritumoral enhancement in CECT”, “alpha-fetoprotein level > 200 ng/Ml,” “halo in US,” “capsule enhancement in CECT,” and “posterior acoustic enhancement in US.” The area under the curve (AUC) values for the training and validation cohorts were 0.824 and 0.725, respectively. The Hosmer–Lemeshow fit test showed no statistical difference (p = 0.369 and p = 0.067 for the training and validation cohorts, respectively). DCA demonstrated that our nomogram provided clinical benefits to a wide range of patients. According to the nomogram score, the VETC-positive and -negative groups demonstrated significant differences in both the training (p < 0.001) and validation (p = 0.001) cohorts. ConclusionOur prediction model based on US and CECT imaging features can accurately predict VETC in HCC.

Development and temporal validation of a clinical prediction model of transition to psychosis in individuals at ultra-high risk in the UHR 1000+ cohort.

The concept of ultra-high risk for psychosis (UHR) has been at the forefront of psychiatric research for several decades, with the ultimate goal of preventing the onset of psychotic disorder in high-risk individuals. Orygen (Melbourne, Australia) has led a range of observational and intervention studies in this clinical population. These datasets have now been integrated into the UHR 1000+ cohort, consisting of a sample of 1,245 UHR individuals with a follow-up period ranging from 1 to 16.7 years. This paper describes the cohort, presents a clinical prediction model of transition to psychosis in this cohort, and examines how predictive performance is affected by changes in UHR samples over time. We analyzed transition to psychosis using a Cox proportional hazards model. Clinical predictors for transition to psychosis were investigated in the entire cohort using multiple imputation and Rubin's rule. To assess performance drift over time, data from 1995-2016 were used for initial model fitting, and models were subsequently validated on data from 2017-2020. Over the follow-up period, 220 cases (17.7%) developed a psychotic disorder. Pooled hazard ratio (HR) estimates showed that the Comprehensive Assessment of At-Risk Mental States (CAARMS) Disorganized Speech subscale severity score (HR=1.12, 95% CI: 1.02-1.24, p=0.024), the CAARMS Unusual Thought Content subscale severity score (HR=1.13, 95% CI: 1.03-1.24, p=0.009), the Scale for the Assessment of Negative Symptoms (SANS) total score (HR=1.02, 95% CI: 1.00-1.03, p=0.022), the Social and Occupational Functioning Assessment Scale (SOFAS) score (HR=0.98, 95% CI: 0.97-1.00, p=0.036), and time between onset of symptoms and entry to UHR service (log transformed) (HR=1.10, 95% CI: 1.02-1.19, p=0.013) were predictive of transition to psychosis. UHR individuals who met the brief limited intermittent psychotic symptoms (BLIPS) criteria had a higher probability of transitioning to psychosis than those who met the attenuated psychotic symptoms (APS) criteria (HR=0.48, 95% CI: 0.32-0.73, p=0.001) and those who met the Trait risk criteria (a first-degree relative with a psychotic disorder or a schizotypal personality disorder plus a significant decrease in functioning during the previous year) (HR=0.43, 95% CI: 0.22-0.83, p=0.013). Models based on data from 1995-2016 displayed good calibration at initial model fitting, but showed a drift of 20.2-35.4% in calibration when validated on data from 2017-2020. Large-scale longitudinal data such as those from the UHR 1000+ cohort are required to develop accurate psychosis prediction models. It is critical to assess existing and future risk calculators for temporal drift, that may reduce their utility in clinical practice over time.

Addressing the implementation challenge of risk prediction model due to missing risk factors: The submodel approximation approach.

Clinical prediction models have been widely acknowledged as informative tools providing evidence-based support for clinical decision making. However, prediction models are often underused in clinical practice due to many reasons including missing information upon real-time risk calculation in electronic health records (EHR) system. Existing literature to address this challenge focuses on statistical comparison of various approaches while overlooking the feasibility of their implementation in EHR. In this article, we propose a novel and feasible submodel approach to address this challenge for prediction models developed using the model approximation (also termed "preconditioning") method. The proposed submodel coefficients are equivalent to the corresponding original prediction model coefficients plus a correction factor. Comprehensive simulations were conducted to assess the performance of the proposed method and compared with the existing "one-step-sweep" approach as well as the imputation approach. In general, the simulation results show the preconditioning-based submodel approach is robust to various heterogeneity scenarios and is comparable to the imputation-based approach, while the "one-step-sweep" approach is less robust under certain heterogeneity scenarios. The proposed method was applied to facilitate real-time implementation of a prediction model to identify emergency department patients with acute heart failure who can be safely discharged home.

A scoring-based clinical grading model for xanthelasma palpebrarum: predicting treatment frequency and prognosis.

Xanthelasma palpebrarum is one of the most common cutaneous xanthomas in humans. Currently, there are various methods available for treating xanthelasma palpebrarum, but the high treatment frequency and recurrence rate remain significant challenges for patients. Therefore, it is necessary to establish a reasonable and effective clinical grading system to guide the diagnosis and treatment of xanthelasma palpebrarum. We developed a clinical scoring system related to local injection of pingyangmycin for the treatment of xanthelasma palpebrarum, which can be used to predict early prognosis and treatment outcomes in patients. We collected and retrospectively studied 246 outpatient cases of xanthelasma palpebrarum treated with local injection of pingyangmycin in the Department of Plastic Surgery at Shanghai East Hospital from February 2020 to August 2022. Potential independent risk factors for adverse outcomes (recurrence or non-recurrence) were considered in univariate and multivariate logistic regression models. Predictive factors were determined based on the multivariate logistic regression model and Cox model, and a scoring grading system was established. External validation was conducted on an independent cohort of 110 patients. Based on logistic regression analysis, the number, area, and color of lesions were identified as significant predictive indicators (P < 0.05), with respective AUCs of 0.710, 0.799, and 0.755. The Cox model established hazard ratios for four new severity indicators of xanthelasma palpebrarum: hyperlipidemia, number of lesions, lesion area, and lesion grayscale value. Based on these findings, a new clinical grading model was developed, which was validated to be effective in the external cohort. The new scoring-based clinical predictive model can effectively predict the number of pingyangmycin injection treatments and prognosis in patients with xanthelasma palpebrarum. It holds promise for broader application in clinical practice.

Application of a combined clinical prediction model based on enhanced T1-weighted image(T1WI) full volume histogram in peripheral nerve invasion (PNI) and lymphatic vessel invasion (LVI) in rectal cancer.

This study aims to use a combined clinical prediction model based on enhanced T1-weighted image(T1WI) full volume histogram to predict preoperative peripheral nerve invasion (PNI) and lymphatic vessel invasion (LVI) in rectal cancer. We included a total of 68 PNI patients and 80 LVI patients who underwent surgical resection and pathological confirmation of rectal cancer. According to the PNI/LVI status, patients were divided into PNI positive group (n = 39), the PNI negative group (n = 29), LVI positive group (n = 48), and the LVI negative group (n = 32). External validation included a total of 42 patients with nerve and vascular invasion in patients with surgically resected and pathologically confirmed rectal cancer at another healthcare facility, with a PNI positive group (n = 32) and a PNI-negative group (n = 10) as well as an LVI positive group (n = 35) and LVI-negative group (n = 7). All patients underwent 3.0T magnetic resonance T1WI enhanced scanning. We use Firevoxel software to delineate the region of interest (ROI), extract histogram parameters, and perform univariate analysis, LASSO regression, and multivariate logistic regression analysis in sequence to screen for the best predictive factors. Then, we constructed a clinical prediction model and plotted it into a column chart for personalized prediction. Finally, we evaluate the performance and clinical practicality of the model based on the area under curve (AUC), calibration curve, and decision curve. Multivariate logistic regression analysis found that variance and the 75th percentile were independent risk factors for PNI, while maximum and variance were independent risk factors for LVI. The clinical prediction model constructed based on the above factors has an AUC of 0.734 (95% CI: 0.591-0.878) for PNI in the training set and 0.731 (95% CI: 0.509-0.952) in the validation set; The training set AUC of LVI is 0.701 (95% CI: 0.561-0.841), and the validation set AUC is 0.685 (95% CI: 0.439-0.932). External validation showed an AUC of 0.722 (95% CI: 0.565-0.878) for PNI; and an AUC of 0.706 (95% CI: 0.481-0.931) for LVI. This study indicates that the combination of enhanced T1WI full volume histogram and clinical prediction model can be used to predict the perineural and lymphovascular invasion status of rectal cancer before surgery, providing valuable reference information for clinical diagnosis.

Ethical considerations of use of hold-out sets in clinical prediction model management

AbstractClinical prediction models are statistical or machine learning models used to quantify the risk of a certain health outcome using patient data. These can then inform potential interventions on patients, causing an effect called performative prediction: predictions inform interventions which influence the outcome they were trying to predict, leading to a potential underestimation of risk in some patients if a model is updated on this data. One suggested resolution to this is the use of hold-out sets, in which a set of patients do not receive model derived risk scores, such that a model can be safely retrained. We present an overview of clinical and research ethics regarding potential implementation of hold-out sets for clinical prediction models in health settings. We focus on the ethical principles of beneficence, non-maleficence, autonomy and justice. We also discuss informed consent, clinical equipoise, and truth-telling. We present illustrative cases of potential hold-out set implementations and discuss statistical issues arising from different hold-out set sampling methods. We also discuss differences between hold-out sets and randomised control trials, in terms of ethics and statistical issues. Finally, we give practical recommendations for researchers interested in the use hold-out sets for clinical prediction models.

Systematic Review of Clinical Prediction Models for the Risk of Emergency Caesarean Births.

Globally, caesarean births (CB), including emergency caesareans births (EmCB), are rising. It is estimated that nearly a third of all births will be CB by 2030. Identify and summarise the results from studies developing and validating prognostic multivariable models predicting the risk of EmCBs. Ultimately understanding the accuracy of their development, and whether they are operationalised for use in routine clinical practice. Studies were identified using databases: MEDLINE, CINAHL, Cochrane Central and Scopus with a search strategy tailored to models predicting EmCBs. Prospective studies developing and validating clinical prediction models, with two or more covariates, to predict risk of EmCB. Data were extracted onto a proforma using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). In total, 8083 studies resulted in 56 unique prediction modelling studies and seven validating studies, with a total of 121 different predictors. Frequently occurring predictors included maternal height, maternal age, parity, BMI and gestational age. PROBAST highlighted 33 studies with low overall bias, and these all internally validated their model. Thirteen studies externally validated; only eight of these were graded an overall low risk of bias. Six models offered applications that could be readily used, but only one provided enough time to offer a planned caesarean birth (pCB). These well-refined models have not been recalibrated since development. Only one model, developed in a relatively low-risk population, with data collected a decade ago, remains useful at 36 weeks for arranging a pCB. To improve personalised clinical conversations, there is a pressing need for a model that accurately predicts the timely risk of an EmCB for women across diverse clinical backgrounds. PROSPERO registration number: CRD42023384439.

Predicting treatment resistance in positive and negative symptom domains from first episode psychosis: Development of a clinical prediction model

BackgroundTreatment resistance (TR) in schizophrenia may be defined by the persistence of positive and/or negative symptoms despite adequate treatment. Whilst previous investigations have focused on positive symptoms, negative symptoms are highly prevalent, impactful, and difficult to treat. In the current study we aimed to develop easily employable prediction models to predict TR in positive and negative symptom domains from first episode psychosis (FEP). MethodsLongitudinal cohort data from 1027 individuals with FEP was utilised. Using a robust definition of TR, n = 51 (4.97 %) participants were treatment resistant in the positive domain and n = 56 (5.46 %) treatment resistant in the negative domain 12 months after first presentation. 20 predictor variables, selected by existing evidence and availability in clinical practice, were entered into two LASSO regression models. We estimated the models using repeated nested cross-validation (NCV) and assessed performance using discrimination and calibration measures. ResultsThe prediction model for TR in the positive domain showed good discrimination (AUC = 0.72). Twelve predictor variables (male gender, cannabis use, age, positive symptom severity, depression and academic and social functioning) were retained by each outer fold of the NCV procedure, indicating importance in prediction of the outcome. However, our negative domain model failed to discriminate those with and without TR, with results only just over chance (AUC = 0.56). ConclusionsTreatment resistance of positive symptoms can be accurately predicted from FEP using routinely collected baseline data, however prediction of negative domain-TR remains a challenge. Detailed negative symptom domains, clinical data, and biomarkers should be considered in future longitudinal studies.

Construction of a clinical prediction model for the diagnosis of immune thrombocytopenia based on clinical laboratory parameters

PurposePrimary immune thrombocytopenia (ITP) is an autoimmune bleeding disorder characterized by isolated thrombocytopenia that is often misdiagnosed due to the lack of a gold standard for diagnosis and currently relies on exclusionary approaches. This project combines several laboratory parameters to construct a clinical prediction model for adult ITP patients.MethodsA total of 428 patients with thrombocytopenia who visited the West China Hospital of Sichuan University between January 2021 and March 2023 were enrolled. Based on the diagnostic criteria, we divided those patients into an ITP group and a non-ITP group. A total of 34 laboratory parameters were analyzed via univariate analysis and correlation analysis, and the least absolute shrinkage and selection operator regression analysis was used to establish the model. The training and validation sets were divided at a ratio of 7:3, and we used a fivefold cross-validation method to construct the model.ResultsThe model included the following variables: red blood cell, mean corpuscular hemoglobin concentration, red blood cell distribution width-standard deviation, platelet variability index score, immature platelet fraction, lymphocyte absolute value. The prediction model exhibited good performance, with a sensitivity of 0.89 and a specificity of 0.83 in the training set and a sensitivity of 0.90 and a specificity of 0.87 in the validation set.ConclusionThe clinical prediction model can assess the probability of ITP in thrombocytopenic patients and has good predictive accuracy for the diagnosis of ITP.

Prediction factors and models for chronic kidney disease in type 2 diabetes mellitus: A review of the literature

AbstractDiabetes mellitus (DM) has become a major chronic disease seriously affecting human health. Type 2 diabetes mellitus (T2DM) accounts for about 90% of DM patients, which is the largest type. Approximately 25–35% of T2DM patients develop kidney disease, which not only impacts the survival rate and quality of life but also, to the family and society, are of great economic burden. Early identification of high‐risk T2DM patients with kidney disease is crucial for initiating targeted prevention and treatment measures in time to reduce or delay the occurrence and progression of diabetic kidney disease. Previous studies have identified a variety of clinical predictors for the progression of renal function in T2DM patients, including proteinuria, estimated glomerular filtration rate, blood glucose, blood pressure, serum uric acid, dyslipidemia, obesity, smoking, duration of DM, age, gender, race, family history of DM, and diabetic retinopathy. Clinical prediction models based on conventional clinical indicators are instrumental in evaluating the risk of kidney disease in T2DM patients, assisting in patient risk stratification. This article systematically reviews the clinical prediction factors and prediction models associated with the progression of renal function in T2DM patients, providing a comprehensive and current reference for improved clinical assessment of the risk of renal function progression.