Accuracy of Machine Learning Models to Predict Mortality in COVID-19 Infection Using the Clinical and Laboratory Data at the Time of Admission

Artificial intelligence-driven prediction of COVID-19-related hospitalization and death: a systematic review

Aim

To perform a systematic review on the use of Artificial Intelligence (AI) techniques for predicting COVID-19 hospitalization and mortality using primary and secondary data sources.

Study eligibility criteria

Cohort, clinical trials, meta-analyses, and observational studies investigating COVID-19 hospitalization or mortality using artificial intelligence techniques were eligible. Articles without a full text available in the English language were excluded.

Data sources

Articles recorded in Ovid MEDLINE from 01/01/2019 to 22/08/2022 were screened.

Data extraction

We extracted information on data sources, AI models, and epidemiological aspects of retrieved studies.

Bias assessment

A bias assessment of AI models was done using PROBAST.

Participants

Patients tested positive for COVID-19.

Results

We included 39 studies related to AI-based prediction of hospitalization and death related to COVID-19. The articles were published in the period 2019-2022, and mostly used Random Forest as the model with the best performance. AI models were trained using cohorts of individuals sampled from populations of European and non-European countries, mostly with cohort sample size <5,000. Data collection generally included information on demographics, clinical records, laboratory results, and pharmacological treatments (i.e., high-dimensional datasets). In most studies, the models were internally validated with cross-validation, but the majority of studies lacked external validation and calibration. Covariates were not prioritized using ensemble approaches in most of the studies, however, models still showed moderately good performances with Area under the Receiver operating characteristic Curve (AUC) values >0.7. According to the assessment with PROBAST, all models had a high risk of bias and/or concern regarding applicability.

Conclusions

A broad range of AI techniques have been used to predict COVID-19 hospitalization and mortality. The studies reported good prediction performance of AI models, however, high risk of bias and/or concern regarding applicability were detected.

Developing an Artificial Intelligence Model for Tumor Grading and Classification, Based on MRI Sequences of Human Brain Gliomas

Background: Artificial intelligence (AI) models have provided advanced applications to many scientific areas, including the prediction of the pathologic grade of tumors, utilizing radiology techniques. Gliomas are among the malignant brain tumors in human adults, and their efficient diagnosis is of high clinical significance. Objectives: Given the contribution of AI to medical diagnoses, we investigated the role of deep learning in the differential diagnosis and grading of human brain gliomas. Methods: This study developed a new AI diagnostic model, i.e., EfficientNetB0, to grade and classify human brain gliomas, using sequences from magnetic resonance imaging (MRI). Results: We validated the new AI model, using a standard dataset (BraTS-2019) and demonstrated that the AI components, i.e., convolutional neural networks and transfer learning, provided excellent performance for classifying and grading glioma images at 98.8% accuracy. Conclusions: The proposed model, EfficientNetB0, is capable to classify and grade glioma from MRI sequences at high accuracy, validity, and specificity. It can provide better performance and diagnostic results for human glioma images than models developed by previous studies.

Improving the Accuracy of Predictive Models for Outcomes of Antidepressants by Using an Ontological Adjustment Approach

For patients with rare comorbidities, there are insufficient observations to accurately estimate the effectiveness of treatment. At the same time, all diagnosis, including rare diagnosis, are part of the International Classification of Disease (ICD). Grouping ICD into broader concepts (i.e., ontology adjustment) can not only increase accuracy of estimating antidepressant effectiveness for patients with rare conditions but also prevent overfitting in big data analysis. In this study, 3,678,082 depressed patients treated with antidepressants were obtained from OptumLabs® Data Warehouse (OLDW). For rare diagnoses, adjustments were made by using the likelihood ratio of the immediate broader concept in the ICD hierarchies. The accuracy of models in training (90%) and test (10%) sets was examined using the area under the receiver operating curves (AROC). The gap in training and test AROC shows how much random noise was modeled. If the gap is large, then the parameters of the model, including the reported effectiveness of the antidepressant for patients with rare conditions, are suspect. There was, on average, a 9.0% reduction in the AROC gap after using the ontological adjustment. Therefore, ontology adjustment can reduce model overfitting, leading to better parameter estimates from the training set.