Segmentation of patients with small cell lung cancer into responders and non-responders using the optimal cross-validation technique.

BACKGROUND: The timing of treating cancer patients is an essential factor in the efficacy of treatment. So, patients who will not respond to current therapy should receive a different treatment as early as possible. Machine learning models can be built to classify responders and nonresponders. Such classification models predict the probability of a patient being a responder. Most methods use a probability threshold of 0.5 to convert the probabilities into binary group membership. However, the cutoff of 0.5 is not always the optimal choice. METHODS: In this study, we propose a novel data-driven approach to select a better cutoff value based on the optimal cross-validation technique. To illustrate our novel method, we applied it to three clinical trial datasets of small-cell lung cancer patients. We used two different datasets to build a scoring system to segment patients. Then the models were applied to segment patients into the test data. RESULTS: We found that, in test data, the predicted responders and non-responders had significantly different long-term survival outcomes. Our proposed novel method segments patients better than the standard approach using a cutoff of 0.5. Comparing clinical outcomes of responders versus non-responders, our novel method had a p-value of 0.009 with a hazard ratio of 0.668 for grouping patients using the Cox proportion hazard model and a p-value of 0.011 using the accelerated failure time model which approved a significant difference between responders and non-responders. In contrast, the standard approach had a p-value of 0.194 with a hazard ratio of 0.823 using the Cox proportion hazard model and a p-value of 0.240 using the accelerated failure time model indicating the responders and non-responders do not differ significantly in survival. CONCLUSION: In summary, our novel prediction method can successfully segment new patients into responders and non-responders. Clinicians can use our prediction to decide if a patient should receive a different treatment or stay with the current treatment.

Effect of vitamin A supplementation on the outcome severity of COVID-19 in hospitalized patients: A pilot randomized clinical trial.

INTRODUCTION: Vitamin A is one of the vitamins that is suggested as adjuvant therapy in viral infections due to its immune enhancing role. In the present clinical trial, we intended to assess the effect of vitamin A supplementation on Coronavirus disease-2019 (COVID-19) in hospitalized patients. METHODS: The present pilot randomized controlled clinical trial was conducted on 30 hospitalized patients with COVID-19. Patients in the intervention group received 50000 IU/day intramuscular vitamin A for a maximum of two weeks. Patients in the control group continued their common treatment protocols. All participants were followed up until discharge from the hospital or death. The primary outcome of the study was time to achieve clinical response based on the six classes of an ordinal scale. Time to clinical response was calculated based on the days needed to improve two scores on the scale or patient's discharge. RESULTS: The time to clinical response was not significantly different between the two groups (7.23 ± 2.14 vs. 6.75 ± 1.85 days, respectively, p = 0.48). There was no significant difference between the groups regarding clinical response (hazard ratio: 1.76 [95% CI: 0.73, 4.26]). There were no significant differences between groups regarding the need for mechanical ventilation, duration of hospitalization, or death in the hospital. CONCLUSION: The results of this pilot clinical trial showed no benefit of vitamin A compared with the common treatment on outcome severity in hospitalized patients with COVID-19. Although the results are negative, there is still a great need for future clinical studies to provide a higher level of evidence.

A Systematic Evaluation of Supervised Machine Learning Algorithms for Cell Phenotype Classification Using Single-Cell RNA Sequencing Data.

The new technology of single-cell RNA sequencing (scRNA-seq) can yield valuable insights into gene expression and give critical information about the cellular compositions of complex tissues. In recent years, vast numbers of scRNA-seq datasets have been generated and made publicly available, and this has enabled researchers to train supervised machine learning models for predicting or classifying various cell-level phenotypes. This has led to the development of many new methods for analyzing scRNA-seq data. Despite the popularity of such applications, there has as yet been no systematic investigation of the performance of these supervised algorithms using predictors from various sizes of scRNA-seq datasets. In this study, 13 popular supervised machine learning algorithms for cell phenotype classification were evaluated using published real and simulated datasets with diverse cell sizes. This benchmark comprises two parts. In the first, real datasets were used to assess the computing speed and cell phenotype classification performance of popular supervised algorithms. The classification performances were evaluated using the area under the receiver operating characteristic curve, F1-score, Precision, Recall, and false-positive rate. In the second part, we evaluated gene-selection performance using published simulated datasets with a known list of real genes. The results showed that ElasticNet with interactions performed the best for small and medium-sized datasets. The NaiveBayes classifier was found to be another appropriate method for medium-sized datasets. With large datasets, the performance of the XGBoost algorithm was found to be excellent. Ensemble algorithms were not found to be significantly superior to individual machine learning methods. Including interactions in the ElasticNet algorithm caused a significant performance improvement for small datasets. The linear discriminant analysis algorithm was found to be the best choice when speed is critical; it is the fastest method, it can scale to handle large sample sizes, and its performance is not much worse than the top performers.

Elevated Liver Aminotransferases Level and COVID-19 Prognosis in Hospitalized Patients: A Prospective Study from Iran.

BACKGROUND: Considering the conflicting results and limited studies on the association between elevated liver enzyme levels and COVID-19 outcomes, in the present study, we aimed to investigate the association between hepatic enzyme changes and the prognosis of COVID-19 during hospital admission. METHODS: In this prospective study, 1017 consecutive patients with COVID-19 participated and were followed up from admission until they were discharged or deceased. The liver enzyme levels were recorded on admission. The patient/disease-related information was recorded by trained nurses using questionnaires. The primary endpoint was the association between elevated liver enzymes and liver injury and mortality from COVID. RESULTS: The mean age of the participants was 62.58±17.45 years; 55.4% of them were male. There was no significant difference between groups regarding the COVID-19 outcomes except for the need for ICU admission (P=0.02). Moreover, all COVID-19 outcomes were significantly higher in patients with liver injury compared with other patients except for the quick sequential organ failure assessment (qSOFA) score. After adjusting for covariates, the patients with Alanine aminotransferase (ALT) and Aspartate aminotransferase (AST) levels of more than 40 (IU/L) and participants with liver injury on admission had significantly greater odds of death, ICU admission, and mechanical ventilation requirements. CONCLUSION: The results of the present study support the hypothesis that poor outcomes of COVID-19 infection were higher in patients with elevated liver enzyme levels and liver injury. Therefore, liver chemicals should be closely monitored during the illness and hospital admission, and patients with COVID-19 and an elevated level of transaminases should be followed up carefully, and necessary interventions should be considered to prevent poor outcomes.

Anemia predicts poor outcomes of COVID-19 in hospitalized patients: a prospective study in Iran.

BACKGROUND: There are limited number of studies with controversial findings regarding the association between anemia at admission and coronavirus disease 2019 (COVID-19) outcomes. Therefore, in this research, we aimed to investigate the prospective association between anemia and COVID-19 outcomes in hospitalized patients in Iran. METHODS: In this prospective study, the data of 1274 consecutive patients hospitalized due to COVID-19 were statistically analyzed. All biomarkers, including hemoglobin and high-sensitivity C-reactive protein (hs-CRP) levels were measured using standard methods. Anemia was defined as a hemoglobin (Hb) concentration of less than 13 g/dL and 12 g/dL in males and females, respectively. Assessing the association between anemia and COVID-19 survival in hospitalized patients was our primary endpoint. RESULTS: The mean age of the participants was 64.43 ± 17.16 years, out of whom 615 (48.27%) were anemic subjects. Patients with anemia were significantly older (P = 0.02) and had a higher frequency of cardiovascular diseases, hypertension, kidney disease, diabetes, and cancer (P < 0.05). The frequency of death (anemic: 23.9% vs. nonanemic: 13.8%), ICU admission (anemic: 27.8% vs. nonanemic:14.71%), and ventilator requirement (anemic: 35.93% vs. nonanemic: 20.63%) were significantly higher in anemic patients than in nonanemic patients (P < 0.001). According to the results of regression analysis, after adjusting for significant covariate in the univariable model, anemia was independently associated with mortality (OR: 1.68, 95% CI: 1.10, 2.57, P = 0.01), ventilator requirement (OR: 1.74, 95% CI: 1.19, 2.54, P = 0.004), and the risk of ICU admission (OR: 2.06, 95% CI: 1.46, 2.90, P < 0.001). CONCLUSION: The prevalence of anemia in hospitalized patients with COVID-19 was high and was associated with poor outcomes of COVID-19.