Covariate dependent Markov chains constructed with gradient boost modeling can effectively generate long-term predictions of obesity trends

Abstract

Importance: The prevalence of obesity among United States adults has increased from 30.5% in 1999 to 41.9% in 2020. However, despite the recognition of long-term weight gain as an important public health issue, there is a paucity of studies studying the long-term weight gain and building models for long-term projection. Methods: A retrospective, cross-sectional cohort study using the publicly available National Health and Nutrition Examination Survey (NHANES 2017–2020) was conducted in patients who completed the weight questionnaire and had accurate data for both weight at time of survey and weight ten years ago. Multistate gradient boost modeling classifiers were used to generate covariate dependent transition matrices and Markov chains were utilized for multistate modeling. Results: Of the 6,146 patients that met the inclusion criteria, 3,024 (49%) of patients were male and 3,122 (51%) of patients were female. There were 2,252 (37%) White patients, 1,257 (20%) Hispanic patients, 1,636 (37%) Black patients, and 739 (12%) Asian patients. The average BMI was 30.16 (SD = 7.15), the average weight was 83.67 kilos (SD = 22.04), and the average weight change was a 3.27 kg (SD = 14.97) increase in body weight (Fig. 1). A total of 2,411 (39%) patients lost weight, and 3,735 (61%) patients gained weight (Table 1). We observed that 87 (1%) of patients were underweight (BMI < 18.5), 2,058 (33%) were normal weight (18.5 ≤ BMI < 25), 1,376 (22%) were overweight (25 ≤ BMI < 30) and 2,625 (43%) were obese (BMI > 30). From analysis of the transitions between normal/underweight, overweight, and obese, we observed that after 10 years, of the patients who were underweight, 65% stayed underweight, 32% became normal weight, 2% became overweight, and 2% became obese. After 10 years, of the patients who were normal weight, 3% became underweight, 78% stayed normal weight, 17% became overweight, and 2% became obese. Of the patients who were overweight, 71% stayed overweight, 0% became underweight, 14% became normal weight, and 15% became obese. Of the patients who were obese, 84% stayed obese, 0% became underweight, 1% became normal weight, and 14% became overweight. Conclusions: United States adults are at risk of transitioning from normal weight to becoming overweight or obese. Covariate dependent Markov chains constructed with gradient boost modeling can effectively generate long-term predictions.

Chronic Diseases: A Comprehensive Review of Applications for Prediction of Obesity

“…For instance, ML can predict which individuals are at higher risk of obesity or its related complications based on their genetic makeup, behaviour patterns, and even social determinants of health [21,26,41,42]. This allows for earlier and more targeted interventions, potentially preventing the onset of obesity rather than merely attempting to reverse it [28,30,[43][44][45]. Furthermore, predictive analytics can help monitor the effectiveness of prescribed interventions in real-time, allowing for adjustments that improve outcomes [25,39,46,47].…”