Early prediction of patient mortality risks during a pandemic can decrease mortality by assuring efficient resource allocation and treatment planning. This study aimed to develop and compare prognosis prediction machine learning models based on invasive laboratory and noninvasive clinical and demographic data from patients’ day of admission. Three Support Vector Machine (SVM) models were developed and compared using invasive, non-invasive, and both groups. The results suggested that non-invasive features could provide mortality predictions that are similar to the invasive and roughly on par with the joint model. Feature inspection results from SVM-RFE and sparsity analysis displayed that, compared with the invasive model, the non-invasive model can provide better performances with a fewer number of features, pointing to the presence of high predictive information contents in several non-invasive features, including SPO2, age, and cardiovascular disorders. Furthermore, while the invasive model was able to provide better mortality predictions for the imminent future, non-invasive features displayed better performance for more distant expiration intervals. Early mortality prediction using non-invasive models can give us insights as to where and with whom to intervene. Combined with novel technologies, such as wireless wearable devices, these models can create powerful frameworks for various medical assignments and patient triage.

Background Due to the increasing worldwide prevalence of obesity, it is essential to determine the prevalence of obesity-related thyroid dysfunctions. The purpose of this study was to investigate the prevalence of thyroid dysfunctions, namely hypothyroidism and hyperthyroidism, and their association with BMI among adult Iranian overweight and obese individuals. Method This cross-sectional study was carried out within the framework of the Tehran Thyroid Study (TTS); 5353 participants (57.5% female) entered our study. Anthropometric measurements were performed. Serum levels of thyroid-stimulating hormone (TSH), free thyroxine (FT4), and thyroid peroxidase antibody (TPOAb) were assayed. We categorized individuals into 3 BMI groups (normal-weight, overweight and obese), then calculated prevalence rate, odds ratio (OR), and 95% confidence interval (CI) for outcomes in overweight and obese groups. The normal-weight group was used as the control group. Results We found a higher prevalence of hypothyroidism (11.6% vs 8.2% Total, 4.0% vs 1.1% overt and 7.6% vs 7.1% subclinical, P < 0.001) and TPOAb positivity (17.3% vs 11.6%, P < 0.001) in obese participants compared with normal-weight participants. Hyperthyroidism’s overall prevalence was 4.2, 5.7, and 4.9% in obese, overweight, and normal-weight groups, respectively. Obesity was associated with higher odds of overt hypothyroidism (OR: 2.0, 95% CI: 1.15–3.49, P < 0.05) and TPOAb positivity (OR: 1.29, 95% CI: 1.04–1.60, P < 0.05) after adjusting for confounding variables. In contrast, no association was observed between the overweight group and the odds of hypothyroidism and TPOAb positivity in the adjusted results. Conclusions Obesity was associated with an increased risk of overt hypothyroidism and TPOAb positivity.