Use of machine learning to identify risk factors for insomnia.

IMPORTANCE: Sleep is critical to a person's physical and mental health, but there are few studies systematically assessing risk factors for sleep disorders. OBJECTIVE: The objective of this study was to identify risk factors for a sleep disorder through machine-learning and assess this methodology. DESIGN, SETTING, AND PARTICIPANTS: A retrospective, cross-sectional cohort study using the publicly available National Health and Nutrition Examination Survey (NHANES) was conducted in patients who completed the demographic, dietary, exercise, and mental health questionnaire and had laboratory and physical exam data. METHODS: A physician diagnosis of insomnia was the outcome of this study. Univariate logistic models, with insomnia as the outcome, were used to identify covariates that were associated with insomnia. Covariates that had a p<0.0001 on univariate analysis were included within the final machine-learning model. The machine learning model XGBoost was used due to its prevalence within the literature as well as its increased predictive accuracy in healthcare prediction. Model covariates were ranked according to the cover statistic to identify risk factors for insomnia. Shapely Additive Explanations (SHAP) were utilized to visualize the relationship between these potential risk factors and insomnia. RESULTS: Of the 7,929 patients that met the inclusion criteria in this study, 4,055 (51% were female, 3,874 (49%) were male. The mean age was 49.2 (SD = 18.4), with 2,885 (36%) White patients, 2,144 (27%) Black patients, 1,639 (21%) Hispanic patients, and 1,261 (16%) patients of another race. The machine learning model had 64 out of a total of 684 features that were found to be significant on univariate analysis (P<0.0001 used). These were fitted into the XGBoost model and an AUROC = 0.87, Sensitivity = 0.77, Specificity = 0.77 were observed. The top four highest ranked features by cover, a measure of the percentage contribution of the covariate to the overall model prediction, were the Patient Health Questionnaire depression survey (PHQ-9) (Cover = 31.1%), age (Cover = 7.54%), physician recommendation of exercise (Cover = 3.86%), weight (Cover = 2.99%), and waist circumference (Cover = 2.70%). CONCLUSION: Machine learning models can effectively predict risk for a sleep disorder using demographic, laboratory, physical exam, and lifestyle covariates and identify key risk factors.

Hospitalized COVID-19 patients with diabetes have an increased risk for pneumonia, intensive care unit requirement, intubation, and death: A cross-sectional cohort study in Mexico in 2020.

Background: Diabetes mellitus is a chronic health condition that has been linked with an increased risk of severe illness and mortality from COVID-19. In Mexico, the impact of diabetes on COVID-19 outcomes in hospitalized patients has not been fully quantified. Understanding the increased risk posed by diabetes in this patient population can help healthcare providers better allocate resources and improve patient outcomes. Objective: The objective of this study was to quantify the extent outcomes (pneumonia, intensive care unit [ICU] stay, intubation, and death) are worsened in diabetic patients with COVID-19. Methods: Between April 14, 2020 and December 20, 2020 (last accessed), data from the open-source COVID-19 database maintained by the Mexican Federal Government were examined. Utilizing hospitalized COVID-19 patients with complete outcome data, a retrospective cohort study (N = 402,388) was carried out. In relation to COVID-19, both univariate and multivariate logistic regression were used to investigate the effect of diabetes on specific outcomes. Results: The analysis included 402,388 adults (age >18) with confirmed hospitalized COVID-19 cases with mean age 46.16 (standard deviation = 15.55), 214,161 (53%) male. The outcomes delineated included pneumonia (N = 88,064; 22%), ICU requirement (N = 23,670; 6%), intubation (N = 23,670; 6%), and death (N = 55,356; 14%). After controlling for confounding variables diabetes continued to be an independent risk factor for both pneumonia (odds ratio [OR]: 1.8, confidence interval [CI]: 1.76-1.84, p < 0.01), ICU requirement (OR: 1.09, CI: 1.04-1.14, p < 0.01), intubation (OR: 1.07, CI: 1.04-1.11, p < 0.01), and death (OR: 1.88, CI: 1.84-1.93, p < 0.01) in COVID-19 patients. Conclusions: According to the study, all outcomes (pneumonia, ICU requirement, intubation, and death) were greater among hospitalized individuals with diabetes and COVID-19. Additional study is required to acquire a better understanding of how diabetes affects COVID-19 outcomes and to develop practical mitigation techniques for the risk of severe sickness and complications in this particular patient population.