BIO-CXRNET: a robust multimodal stacking machine learning technique for mortality risk prediction of COVID-19 patients using chest X-ray images and clinical data.

Nowadays, quick, and accurate diagnosis of COVID-19 is a pressing need. This study presents a multimodal system to meet this need. The presented system employs a machine learning module that learns the required knowledge from the datasets collected from 930 COVID-19 patients hospitalized in Italy during the first wave of COVID-19 (March-June 2020). The dataset consists of twenty-five biomarkers from electronic health record and Chest X-ray (CXR) images. It is found that the system can diagnose low- or high-risk patients with an accuracy, sensitivity, and F1-score of 89.03%, 90.44%, and 89.03%, respectively. The system exhibits 6% higher accuracy than the systems that employ either CXR images or biomarker data. In addition, the system can calculate the mortality risk of high-risk patients using multivariate logistic regression-based nomogram scoring technique. Interested physicians can use the presented system to predict the early mortality risks of COVID-19 patients using the web-link: Covid-severity-grading-AI. In this case, a physician needs to input the following information: CXR image file, Lactate Dehydrogenase (LDH), Oxygen Saturation (O2%), White Blood Cells Count, C-reactive protein, and Age. This way, this study contributes to the management of COVID-19 patients by predicting early mortality risk. Supplementary Information: The online version contains supplementary material available at 10.1007/s00521-023-08606-w.

External validation of the Oldham composite Covid-19 associated mortality model (OCCAM), a prognostic model for death in patients hospitalised with Covid-19.

OBJECTIVE: External validation of the Oldham Composite Covid-19 associated Mortality Model (OCCAM), a prognostic model for Covid-19 mortality in hospitalised patients comprised of age, history of hypertension, current or previous malignancy, admission platelet count < 150 × 103/µL, admission CRP ≥ 100 µg/mL, acute kidney injury (AKI), and radiographic evidence of > 50% total lung field infiltrates. PATIENTS AND METHODS: Retrospective study assessing discrimination (c-statistic) and calibration of OCCAM for death in hospital or within 30 days of discharge. 300 adults admitted to six district general and teaching hospitals in North West England for treatment of Covid-19 between September 2020 and February 2021 were included. RESULTS: Two hundred and ninety-seven patients were included in the validation cohort analysis, with a mortality rate of 32.8%. The c-statistic was 0.794 (95% confidence interval 0.742-0.847) vs. 0.805 (95% confidence interval 0.766 - 0.844) in the development cohort. Visual inspection of calibration plots demonstrate excellent calibration across risk groups, with a calibration slope for the external validation cohort of 0.963. CONCLUSION: The OCCAM model is an effective prognostic tool that can be utilised at the time of initial patient assessment to aid decisions around admission and discharge, use of therapeutics, and shared decision-making with patients. Clinicians should remain aware of the need for ongoing validation of all Covid-19 prognostic models in light of changes in host immunity and emerging variants.

A prognostic model for classification of COVID-19 severity based on clinical and laboratory testing data

This study aimed to build an machine learning based model to predict the COVID-19 severity and reveal risk factors related to COVID-19 severity based on laboratory testing and clinical data for 420 participants, using tree-based models such as XGBoost, LightGBM, random forest. We calculated the Odds Ratios (OR) to investigate whether the top-ranked features were statistically significant for severity classification, turning out that high sensitivity C-reactive protein (hs-CRP) was the most important feature for determining of COVID-19 severity and XGBoost model showed the highest performance in classifying COVID-19 severity and healthy controls with F1score (0.84) and AUC (0.87). We expect that our results are of considerable significance for early screening for diagnosing COVID-19 severity, which, in turn, assist in further retrospective research for uncommon infectious diseases. © 2023 IEEE.

Seven bacterial response-related genes are biomarkers for colon cancer.

BACKGROUND: Colon cancer (CC) is a common tumor that causes significant harm to human health. Bacteria play a vital role in cancer biology, particularly the biology of CC. Genes related to bacterial response were seldom used to construct prognosis models. We constructed a bacterial response-related risk model based on three Molecular Signatures Database gene sets to explore new markers for predicting CC prognosis. METHODS: The Cancer Genome Atlas (TCGA) colon adenocarcinoma samples were used as the training set, and Gene Expression Omnibus (GEO) databases were used as the test set. Differentially expressed bacterial response-related genes were identified for prognostic gene selection. Univariate Cox regression analysis, least absolute shrinkage and selection operator-penalized Cox regression analysis, and multivariate Cox regression analysis were performed to construct a prognostic risk model. The individual diagnostic effects of genes in the prognostic model were also evaluated. Moreover, differentially expressed long noncoding RNAs (lncRNAs) were identified. Finally, the expression of these genes was validated using quantitative polymerase chain reaction (qPCR) in cell lines and tissues. RESULTS: A prognostic signature was constructed based on seven bacterial response genes: LGALS4, RORC, DDIT3, NSUN5, RBCK1, RGL2, and SERPINE1. Patients were assigned a risk score based on the prognostic model, and patients in the TCGA cohort with a high risk score had a poorer prognosis than those with a low risk score; a similar finding was observed in the GEO cohort. These seven prognostic model genes were also independent diagnostic factors. Finally, qPCR validated the differential expression of the seven model genes and two coexpressed lncRNAs (C6orf223 and SLC12A9-AS1) in 27 pairs of CC and normal tissues. Differential expression of LGALS4 and NSUN5 was also verified in cell lines (FHC, COLO320DM, SW480). CONCLUSIONS: We created a seven-gene bacterial response-related gene signature that can accurately predict the outcomes of patients with CC. This model can provide valuable insights for personalized treatment.

B cell-related tertiary lymphoid structure may exert inhibitory effects on lung adenocarcinoma and SARS-COV-2.

Background: The prognosis of lung adenocarcinoma (LUAD) is poor. Infection with coronavirus disease 2019 (COVID-19) may further worsen the outcome of LUAD. This study utilized the immune model and the COVID-19 receptor signal to identify the potential immune structure affecting the prognosis of COVID-19 and LUAD. Methods: A prognostic model was established and verified. The correlation between immune cells and risk score was examined through a variety of immune calculation methods. Gene set variation analysis (GSVA) was used to explore the correlation between the immune signaling pathway, risk model, COVID-19 binding receptor (CO19ORS) signal, and different clinicopathological factors. Results: The analysis showed that the prognosis of patients was better in the low-risk group versus the high-risk group. The tertiary lymphoid structure dominated by T and B cells (TLS1) can improve the prognosis of patients in the low-risk group. Interestingly, the CO19ORS was enriched only in females and aged >65 years. The age group >65 years is closely related to the tertiary lymphatic structure of the newborn (TLS2), while the female sex is closely related to the TLS2 and TLS1 signature. The two groups exhibited a high level of inflammation-related signal distribution. In the near future, I will collect LUAD and COVID-19 related organizations to verify the changes of 8 risk protein. Conclusion: TLS1 structure may improve the prognosis of patients with LUAD and SARS-COV-2 (Severe acute respiratory syndrome coronavirus 2). This unexpected discovery provides new insight into the comprehensive treatment of patients with LUAD and SARS-COV-2.

Development and validation of a prognostic model based on immune variables to early predict severe cases of SARS-CoV-2 Omicron variant infection.

Background: The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Omicron variant has prevailed globally since November 2021. The extremely high transmissibility and occult manifestations were notable, but the severity and mortality associated with the Omicron variant and subvariants cannot be ignored, especially for immunocompromised populations. However, no prognostic model for specially predicting the severity of the Omicron variant infection is available yet. In this study, we aim to develop and validate a prognostic model based on immune variables to early recognize potentially severe cases of Omicron variant-infected patients. Methods: This was a single-center prognostic study involving patients with SARS-CoV-2 Omicron variant infection. Eligible patients were randomly divided into the training and validation cohorts. Variables were collected immediately after admission. Candidate variables were selected by three variable-selecting methods and were used to construct Cox regression as the prognostic model. Discrimination, calibration, and net benefit of the model were evaluated in both training and validation cohorts. Results: Six hundred eighty-nine of the involved 2,645 patients were eligible, consisting of 630 non-ICU cases and 59 ICU cases. Six predictors were finally selected to establish the prognostic model: age, neutrophils, lymphocytes, procalcitonin, IL-2, and IL-10. For discrimination, concordance indexes in the training and validation cohorts were 0.822 (95% CI: 0.748-0.896) and 0.853 (95% CI: 0.769-0.942). For calibration, predicted probabilities and observed proportions displayed high agreements. In the 21-day decision curve analysis, the threshold probability ranges with positive net benefit were 0~1 and nearly 0~0.75 in the training and validation cohorts, correspondingly. Conclusions: This model had satisfactory high discrimination, calibration, and net benefit. It can be used to early recognize potentially severe cases of Omicron variant-infected patients so that they can be treated timely and rationally to reduce the severity and mortality of Omicron variant infection.

How to conduct a systematic review and meta-analysis of prognostic model studies.

BACKGROUND: Prognostic models are typically developed to estimate the risk that an individual in a particular health state will develop a particular health outcome, to support (shared) decision making. Systematic reviews of prognostic model studies can help identify prognostic models that need to further be validated or are ready to be implemented in healthcare. OBJECTIVES: To provide a step-by-step guidance on how to conduct and read a systematic review of prognostic model studies and to provide an overview of methodology and guidance available for every step of the review progress. SOURCES: Published, peer-reviewed guidance articles. CONTENT: We describe the following steps for conducting a systematic review of prognosis studies: 1) Developing the review question using the Population, Index model, Comparator model, Outcome(s), Timing, Setting format, 2) Searching and selection of articles, 3) Data extraction using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) checklist, 4) Quality and risk of bias assessment using the Prediction model Risk Of Bias ASsessment (PROBAST) tool, 5) Analysing data and undertaking quantitative meta-analysis, and 6) Presenting summary of findings, interpreting results, and drawing conclusions. Guidance for each step is described and illustrated using a case study on prognostic models for patients with COVID-19. IMPLICATIONS: Guidance for conducting a systematic review of prognosis studies is available, but the implications of these reviews for clinical practice and further research highly depend on complete reporting of primary studies.

Developing a mortality risk prediction model using data of 3663 hospitalized COVID-19 patients: a retrospective cohort study in an Egyptian University Hospital.

PURPOSE: Since the declaration of COVID-19 as a pandemic, a wide between-country variation was observed regarding in-hospital mortality and its predictors. Given the scarcity of local research and the need to prioritize the provision of care, this study was conducted aiming to measure the incidence of in-hospital COVID-19 mortality and to develop a simple and clinically applicable model for its prediction. METHODS: COVID-19-confirmed patients admitted to the designated isolation areas of Ain-Shams University Hospitals (April 2020-February 2021) were included in this retrospective cohort study (n = 3663). Data were retrieved from patients' records. Kaplan-Meier survival and Cox proportional hazard regression were used. Binary logistic regression was used for creating mortality prediction models. RESULTS: Patients were 53.6% males, 4.6% current smokers, and their median age was 58 (IQR 41-68) years. Admission to intensive care units was 41.1% and mortality was 26.5% (972/3663, 95% CI 25.1-28.0%). Independent mortality predictors-with rapid mortality onset-were age ≥ 75 years, patients' admission in critical condition, and being symptomatic. Current smoking and presence of comorbidities particularly, obesity, malignancy, and chronic haematological disorders predicted mortality too. Some biomarkers were also recognized. Two prediction models exhibited the best performance: a basic model including age, presence/absence of comorbidities, and the severity level of the condition on admission (Area Under Receiver Operating Characteristic Curve (AUC) = 0.832, 95% CI 0.816-0.847) and another model with added International Normalized Ratio (INR) value (AUC = 0.842, 95% CI 0.812-0.873). CONCLUSION: Patients with the identified mortality risk factors are to be prioritized for preventive and rapid treatment measures. With the provided prediction models, clinicians can calculate mortality probability for their patients. Presenting multiple and very generic models can enable clinicians to choose the one containing the parameters available in their specific clinical setting, and also to test the applicability of such models in a non-COVID-19 respiratory infection.

Machine-Learning Approaches for Predicting the Need of Oxygen Therapy in Early-Stage COVID-19 in Japan: Multicenter Retrospective Observational Study.

Background: Early prediction of oxygen therapy in patients with coronavirus disease 2019 (COVID-19) is vital for triage. Several machine-learning prognostic models for COVID-19 are currently available. However, external validation of these models has rarely been performed. Therefore, most reported predictive performance is optimistic and has a high risk of bias. This study aimed to develop and validate a model that predicts oxygen therapy needs in the early stages of COVID-19 using a sizable multicenter dataset. Methods: This multicenter retrospective study included consecutive COVID-19 hospitalized patients confirmed by a reverse transcription chain reaction in 11 medical institutions in Fukui, Japan. We developed and validated seven machine-learning models (e.g., penalized logistic regression model) using routinely collected data (e.g., demographics, simple blood test). The primary outcome was the need for oxygen therapy (≥1 L/min or SpO2 ≤ 94%) during hospitalization. C-statistics, calibration slope, and association measures (e.g., sensitivity) evaluated the performance of the model using the test set (randomly selected 20% of data for internal validation). Among these seven models, the machine-learning model that showed the best performance was re-evaluated using an external dataset. We compared the model performances using the A-DROP criteria (modified version of CURB-65) as a conventional method. Results: Of the 396 patients with COVID-19 for the model development, 102 patients (26%) required oxygen therapy during hospitalization. For internal validation, machine-learning models, except for the k-point nearest neighbor, had a higher discrimination ability than the A-DORP criteria (P < 0.01). The XGboost had the highest c-statistic in the internal validation (0.92 vs. 0.69 in A-DROP criteria; P < 0.001). For the external validation with 728 temporal independent datasets (106 patients [15%] required oxygen therapy), the XG boost model had a higher c-statistic (0.88 vs. 0.69 in A-DROP criteria; P < 0.001). Conclusions: Machine-learning models demonstrated a more significant performance in predicting the need for oxygen therapy in the early stages of COVID-19.

COVID-19-associated lncRNAs as predictors of survival in uterine corpus endometrial carcinoma: A prognostic model.

Background: Patients with uterine corpus endometrial carcinoma (UCEC) may be susceptible to the coronavirus disease-2019 (COVID-19). Long non-coding RNAs take on a critical significance in UCEC occurrence, development, and prognosis. Accordingly, this study aimed to develop a novel model related to COVID-19-related lncRNAs for optimizing the prognosis of endometrial carcinoma. Methods: The samples of endometrial carcinoma patients and the relevant clinical data were acquired in the Carcinoma Genome Atlas (TCGA) database. COVID-19-related lncRNAs were analyzed and obtained by coexpression. Univariate, least absolute shrinkage and selection operator (LASSO), and multivariate Cox regression analyses were performed to establish a COVID-19-related lncRNA risk model. Kaplan-Meier analysis, principal component analysis (PCA), and functional enrichment annotation were used to analyze the risk model. Finally, the potential immunotherapeutic signatures and drug sensitivity prediction targeting this model were also discussed. Results: The risk model comprising 10 COVID-19-associated lncRNAs was identified as a predictive ability for overall survival (OS) in UCEC patients. PCA analysis confirmed a reliable clustering ability of the risk model. By regrouping the patients with this model, different clinic-pathological characteristics, immunotherapeutic response, and chemotherapeutics sensitivity were also observed in different groups. Conclusion: This risk model was developed based on COVID-19-associated lncRNAs which would be conducive to the precise treatment of patients with UCEC.

Development of a prognostic model of COVID-19 severity: a population-based cohort study in Iceland.

BACKGROUND: The severity of SARS-CoV-2 infection varies from asymptomatic state to severe respiratory failure and the clinical course is difficult to predict. The aim of the study was to develop a prognostic model to predict the severity of COVID-19 in unvaccinated adults at the time of diagnosis. METHODS: All SARS-CoV-2-positive adults in Iceland were prospectively enrolled into a telehealth service at diagnosis. A multivariable proportional-odds logistic regression model was derived from information obtained during the enrollment interview of those diagnosed between February 27 and December 31, 2020 who met the inclusion criteria. Outcomes were defined on an ordinal scale: (1) no need for escalation of care during follow-up; (2) need for urgent care visit; (3) hospitalization; and (4) admission to intensive care unit (ICU) or death. Missing data were multiply imputed using chained equations and the model was internally validated using bootstrapping techniques. Decision curve analysis was performed. RESULTS: The prognostic model was derived from 4756 SARS-CoV-2-positive persons. In total, 375 (7.9%) only required urgent care visits, 188 (4.0%) were hospitalized and 50 (1.1%) were either admitted to ICU or died due to complications of COVID-19. The model included age, sex, body mass index (BMI), current smoking, underlying conditions, and symptoms and clinical severity score at enrollment. On internal validation, the optimism-corrected Nagelkerke's R2 was 23.4% (95%CI, 22.7-24.2), the C-statistic was 0.793 (95%CI, 0.789-0.797) and the calibration slope was 0.97 (95%CI, 0.96-0.98). Outcome-specific indices were for urgent care visit or worse (calibration intercept -0.04 [95%CI, -0.06 to -0.02], Emax 0.014 [95%CI, 0.008-0.020]), hospitalization or worse (calibration intercept -0.06 [95%CI, -0.12 to -0.03], Emax 0.018 [95%CI, 0.010-0.027]), and ICU admission or death (calibration intercept -0.10 [95%CI, -0.15 to -0.04] and Emax 0.027 [95%CI, 0.013-0.041]). CONCLUSION: Our prognostic model can accurately predict the later need for urgent outpatient evaluation, hospitalization, and ICU admission and death among unvaccinated SARS-CoV-2-positive adults in the general population at the time of diagnosis, using information obtained by telephone interview.

Facilitating Safe Discharge Through Predicting Disease Progression in Moderate Coronavirus Disease 2019 (COVID-19): A Prospective Cohort Study to Develop and Validate a Clinical Prediction Model in Resource-Limited Settings.

BACKGROUND: In locations where few people have received coronavirus disease 2019 (COVID-19) vaccines, health systems remain vulnerable to surges in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections. Tools to identify patients suitable for community-based management are urgently needed. METHODS: We prospectively recruited adults presenting to 2 hospitals in India with moderate symptoms of laboratory-confirmed COVID-19 to develop and validate a clinical prediction model to rule out progression to supplemental oxygen requirement. The primary outcome was defined as any of the following: SpO2 < 94%; respiratory rate > 30 BPM; SpO2/FiO2 < 400; or death. We specified a priori that each model would contain three clinical parameters (age, sex, and SpO2) and 1 of 7 shortlisted biochemical biomarkers measurable using commercially available rapid tests (C-reactive protein [CRP], D-dimer, interleukin 6 [IL-6], neutrophil-to-lymphocyte ratio [NLR], procalcitonin [PCT], soluble triggering receptor expressed on myeloid cell-1 [sTREM-1], or soluble urokinase plasminogen activator receptor [suPAR]), to ensure the models would be suitable for resource-limited settings. We evaluated discrimination, calibration, and clinical utility of the models in a held-out temporal external validation cohort. RESULTS: In total, 426 participants were recruited, of whom 89 (21.0%) met the primary outcome; 257 participants comprised the development cohort, and 166 comprised the validation cohort. The 3 models containing NLR, suPAR, or IL-6 demonstrated promising discrimination (c-statistics: 0.72-0.74) and calibration (calibration slopes: 1.01-1.05) in the validation cohort and provided greater utility than a model containing the clinical parameters alone. CONCLUSIONS: We present 3 clinical prediction models that could help clinicians identify patients with moderate COVID-19 suitable for community-based management. The models are readily implementable and of particular relevance for locations with limited resources.

Predicting the risk of severe COVID-19 outcomes in primary care: development and validation of a vulnerability index for equitable allocation of effective vaccines.

BACKGROUND: General practitioners (GPs) need a valid, user-friendly tool to identify patients most vulnerable to COVID-19, especially in the hypothesis of a booster vaccine dose. The aim of this study was to develop and validate a GP-friendly prognostic index able to forecast severe COVID-19 outcomes in primary care. Indeed, no such prognostic score is as yet available in Italy. RESEARCH DESIGN AND METHODS: In this retrospective cohort study, a representative sample of 47,868 Italian adults were followed up for 129,000 person-months. The study outcome was COVID-19-related hospitalization and/or death. Candidate predictors were chosen on the basis of systematic evidence and current recommendations. The model was calibrated by using Cox regression. Both internal and external validations were performed. RESULTS: Age, sex and several clinical characteristics were significantly associated with severe outcomes. The final multivariable model explained 60% (95%CI 58-63%) of variance for COVID-19-related hospitalizations and/or deaths. The area under the receiver-operator curve (AUC) was 84% (95% CI: 83-85%). On applying the index to an external cohort, the AUC was 94% (95% CI: 93-95%). CONCLUSIONS: This index is a reliable prognostic tool that can help GPs to prioritize their patients for preventive and therapeutic interventions.

Prognostic Role and Diagnostic Power of Seven Indicators in COVID-19 Patients.

The prognostic role and diagnostic ability of coronavirus disease 2019 (COVID-19) disease indicators are not elucidated, thus, the current study aimed to investigate the prognostic role and diagnostic ability of several COVID-19 disease indicators including the levels of oxygen saturation, leukocytes, lymphocytes, albumin, C-reactive protein (CRP), interleukin-6 (IL-6), and D-dimer in patients with COVID-19. The levels of oxygen saturation, lymphocytes, and albumin were significantly higher in the common and severe clinical type patients compared with those in critical type patients. However, levels of leukocytes, CRP, IL-6, and D-dimer were significantly lower in the common and severe type patients compared with those in critical type patients (P < 0.001). Moreover, the current study demonstrated that the seven indicators have good diagnostic and prognostic powers in patients with COVID-19. Furthermore, a two-indicator (CRP and D-dimer) prognostic signature in training and testing datasets was constructed and validated to better understand the prognostic role of the indicators in COVID-19 patients. The patients were classified into high-risk and low-risk groups based on the median-risk scores. The findings of the Kaplan-Meier curve analysis indicated a significant divergence between the high-risk and low-risk groups. The findings of the receiver operating curve (ROC) analysis indicated the good performance of the signature in the prognosis prediction of COVID-19. In addition, a nomogram was constructed to assist clinicians in developing clinical decision-making for COVID-19 patients. In conclusion, the findings of the current study demonstrated that the seven indicators are potential diagnostic markers for COVID-19 and a two-indicator prognostic signature identification may improve clinical management for COVID-19 patients.

Development and Validation of an Early Scoring System for Prediction of Disease Severity in COVID-19 Using Complete Blood Count Parameters.

The coronavirus disease 2019 (COVID-19) after outbreaking in Wuhan increasingly spread throughout the world. Fast, reliable, and easily accessible clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. The objective of the study was to develop and validate an early scoring tool to stratify the risk of death using readily available complete blood count (CBC) biomarkers. A retrospective study was conducted on twenty-three CBC blood biomarkers for predicting disease mortality for 375 COVID-19 patients admitted to Tongji Hospital, China from January 10 to February 18, 2020. Machine learning based key biomarkers among the CBC parameters as the mortality predictors were identified. A multivariate logistic regression-based nomogram and a scoring system was developed to categorize the patients in three risk groups (low, moderate, and high) for predicting the mortality risk among COVID-19 patients. Lymphocyte count, neutrophils count, age, white blood cell count, monocytes (%), platelet count, red blood cell distribution width parameters collected at hospital admission were selected as important biomarkers for death prediction using random forest feature selection technique. A CBC score was devised for calculating the death probability of the patients and was used to categorize the patients into three sub-risk groups: low (<=5%), moderate (>5% and <=50%), and high (>50%), respectively. The area under the curve (AUC) of the model for the development and internal validation cohort were 0.961 and 0.88, respectively. The proposed model was further validated with an external cohort of 103 patients of Dhaka Medical College, Bangladesh, which exhibits in an AUC of 0.963. The proposed CBC parameter-based prognostic model and the associated web-application, can help the medical doctors to improve the management by early prediction of mortality risk of the COVID-19 patients in the low-resource countries.

Development and validation of a machine-learning ALS survival model lacking vital capacity (VC-Free) for use in clinical trials during the COVID-19 pandemic.

Introduction: Vital capacity (VC) is routinely used for ALS clinical trial eligibility determinations, often to exclude patients unlikely to survive trial duration. However, spirometry has been limited by the COVID-19 pandemic. We developed a machine-learning survival model without the use of baseline VC and asked whether it could stratify clinical trial participants and a wider ALS clinic population. Methods. A gradient boosting machine survival model lacking baseline VC (VC-Free) was trained using the PRO-ACT ALS database and compared to a multivariable model that included VC (VCI) and a univariable baseline %VC model (UNI). Discrimination, calibration-in-the-large and calibration slope were quantified. Models were validated using 10-fold internal cross validation, the VITALITY-ALS clinical trial placebo arm and data from the Emory University tertiary care clinic. Simulations were performed using each model to estimate survival of patients predicted to have a > 50% one year survival probability. Results. The VC-Free model suffered a minor performance decline compared to the VCI model yet retained strong discrimination for stratifying ALS patients. Both models outperformed the UNI model. The proportion of excluded vs. included patients who died through one year was on average 27% vs. 6% (VCI), 31% vs. 7% (VC-Free), and 13% vs. 10% (UNI). Conclusions. The VC-Free model offers an alternative to the use of VC for eligibility determinations during the COVID-19 pandemic. The observation that the VC-Free model outperforms the use of VC in a broad ALS patient population suggests the use of prognostic strata in future, post-pandemic ALS clinical trial eligibility screening determinations.

An Early Warning Tool for Predicting Mortality Risk of COVID-19 Patients Using Machine Learning.

COVID-19 pandemic has created an extreme pressure on the global healthcare services. Fast, reliable, and early clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. In order to study the important blood biomarkers for predicting disease mortality, a retrospective study was conducted on a dataset made public by Yan et al. in [1] of 375 COVID-19 positive patients admitted to Tongji Hospital (China) from January 10 to February 18, 2020. Demographic and clinical characteristics and patient outcomes were investigated using machine learning tools to identify key biomarkers to predict the mortality of individual patient. A nomogram was developed for predicting the mortality risk among COVID-19 patients. Lactate dehydrogenase, neutrophils (%), lymphocyte (%), high-sensitivity C-reactive protein, and age (LNLCA)-acquired at hospital admission-were identified as key predictors of death by multi-tree XGBoost model. The area under curve (AUC) of the nomogram for the derivation and validation cohort were 0.961 and 0.991, respectively. An integrated score (LNLCA) was calculated with the corresponding death probability. COVID-19 patients were divided into three subgroups: low-, moderate-, and high-risk groups using LNLCA cutoff values of 10.4 and 12.65 with the death probability less than 5%, 5-50%, and above 50%, respectively. The prognostic model, nomogram, and LNLCA score can help in early detection of high mortality risk of COVID-19 patients, which will help doctors to improve the management of patient stratification.

Implementation of the COVID-19 Vulnerability Index Across an International Network of Health Care Data Sets: Collaborative External Validation Study.

BACKGROUND: SARS-CoV-2 is straining health care systems globally. The burden on hospitals during the pandemic could be reduced by implementing prediction models that can discriminate patients who require hospitalization from those who do not. The COVID-19 vulnerability (C-19) index, a model that predicts which patients will be admitted to hospital for treatment of pneumonia or pneumonia proxies, has been developed and proposed as a valuable tool for decision-making during the pandemic. However, the model is at high risk of bias according to the "prediction model risk of bias assessment" criteria, and it has not been externally validated. OBJECTIVE: The aim of this study was to externally validate the C-19 index across a range of health care settings to determine how well it broadly predicts hospitalization due to pneumonia in COVID-19 cases. METHODS: We followed the Observational Health Data Sciences and Informatics (OHDSI) framework for external validation to assess the reliability of the C-19 index. We evaluated the model on two different target populations, 41,381 patients who presented with SARS-CoV-2 at an outpatient or emergency department visit and 9,429,285 patients who presented with influenza or related symptoms during an outpatient or emergency department visit, to predict their risk of hospitalization with pneumonia during the following 0-30 days. In total, we validated the model across a network of 14 databases spanning the United States, Europe, Australia, and Asia. RESULTS: The internal validation performance of the C-19 index had a C statistic of 0.73, and the calibration was not reported by the authors. When we externally validated it by transporting it to SARS-CoV-2 data, the model obtained C statistics of 0.36, 0.53 (0.473-0.584) and 0.56 (0.488-0.636) on Spanish, US, and South Korean data sets, respectively. The calibration was poor, with the model underestimating risk. When validated on 12 data sets containing influenza patients across the OHDSI network, the C statistics ranged between 0.40 and 0.68. CONCLUSIONS: Our results show that the discriminative performance of the C-19 index model is low for influenza cohorts and even worse among patients with COVID-19 in the United States, Spain, and South Korea. These results suggest that C-19 should not be used to aid decision-making during the COVID-19 pandemic. Our findings highlight the importance of performing external validation across a range of settings, especially when a prediction model is being extrapolated to a different population. In the field of prediction, extensive validation is required to create appropriate trust in a model.

Integrated Analysis of the Prognosis-Associated RNA-Binding Protein Genes and Candidate Drugs in Renal Papillary Cell Carcinoma.

RNA-binding proteins (RBPs) play significant roles in various cancer types. However, the functions of RBPs have not been clarified in renal papillary cell carcinoma (pRCC). In this study, we identified 31 downregulated and 89 upregulated differentially expressed RBPs on the basis of the cancer genome atlas (TCGA) database and performed functional enrichment analyses. Subsequently, through univariate Cox, random survival forest, and multivariate Cox regression analysis, six RBPs of SNRPN, RRS1, INTS8, RBPMS2, IGF2BP3, and PIH1D2 were screened out, and the prognostic model was then established. Further analyses revealed that the high-risk group had poor overall survival. The area under the curve values were 0.87 and 0.75 at 3 years and 0.78 and 0.69 at 5 years in the training set and test set, respectively. We then plotted a nomogram on the basis of the six RBPs and tumor stage with the substantiation in the TCGA cohort. Moreover, we selected two intersectant RBPs and evaluate their biological effects by GSEA and predicted three drugs, including STOCK1N-28457, pyrimethamine, and trapidil by using the Connectivity Map. Our research provided a novel insight into pRCC and improved the determination of prognosis and individualized therapeutic strategies.