Development of a Clinical Forecasting Model to Predict Comorbid Depression Among Diabetes Patients and an Application in Depression Screening Policy Making

Abstract

IntroductionDepression is a common but often undiagnosed comorbid condition of people with diabetes. Mass screening can detect undiagnosed depression but may require significant resources and time. The objectives of this study were 1) to develop a clinical forecasting model that predicts comorbid depression among patients with diabetes and 2) to evaluate a model-based screening policy that saves resources and time by screening only patients considered as depressed by the clinical forecasting model. MethodsWe trained and validated 4 machine learning models by using data from 2 safety-net clinical trials; we chose the one with the best overall predictive ability as the ultimate model. We compared model-based policy with alternative policies, including mass screening and partial screening, on the basis of depression history or diabetes severity.ResultsLogistic regression had the best overall predictive ability of the 4 models evaluated and was chosen as the ultimate forecasting model. Compared with mass screening, the model-based policy can save approximately 50% to 60% of provider resources and time but will miss identifying about 30% of patients with depression. Partial-screening policy based on depression history alone found only a low rate of depression. Two other heuristic-based partial screening policies identified depression at rates similar to those of the model-based policy but cost more in resources and time.ConclusionThe depression prediction model developed in this study has compelling predictive ability. By adopting the model-based depression screening policy, health care providers can use their resources and time better and increase their efficiency in managing their patients with depression.

Machine Learning and Data Mining Methods in Diabetes Research

“…It is worth noting that DM complications are far less common and severe in people with well-controlled blood glucose levels. Many of those complications have been studied through machine learning and data mining applications [78], [79], [80], [81], [82], [83], [84], [85], [87], [88], [89], [90], [92], [94], [95], [96], [97].…”

“…In [88], authors developed a predictive model exploiting data from two safety-net clinical trials that target comorbid depression, which could be considered as a diabetic complication, among patients with DM. In addition, in [89], authors tried to investigate the effectiveness of e-nose technology, using common classifiers, to predict single- and poly-microbial species targeted for diabetic foot infection.…”

A Method for Predicting Hemolytic Potency of Chemically Modified Peptides From Its Structure

“…There are currently more than a hundred peptide-based drugs in the clinical trial development phases (Lau and Dunn, 2018). However, enthusiasm in peptide research is tempered by some intrinsic limitation of peptides such as immunogenicity (Fernandez et al, 2017), short half-life, proteolytic degradation, low bioavailability (Bruno et al, 2013), and toxicity (Chaudhary et al, 2016). Hemolytic concentration (HC 50 ) is the commonly used indicator of peptide toxicity (Ruiz et al, 2014).…”

Unsupervised Classifications of Depression Levels Based on Machine Learning Algorithms Perform Well as Compared to Traditional Norm-Based Classifications

“…However, depression is widely undiagnosed and thus untreated because of various reasons such as societal stigmas about mental disorders, inefficient tools for diagnosis, and inadequate mentalhealth resources. For example, almost half of the world's population lives in a country with only two psychiatrists per 100,000 people (2), which makes it practically impossible to screen the population for depression with the sanctioned methods of expert interview and clinical diagnosis (6)(7)(8). Moreover, such methods are simply too costly and laborintensive for large-scale screening for depression (9,10).…”

“…Recently, researchers have used machine learning to predict depression from depression-related factors. For example, Jin et al (7) used several classic machine learning methods such as logistic regression, multi-layer perception, and support vector machine to predict depression (measured with Patient Health Questionnaire-9 and Patient Health Questionnaire-2) from common demographic factors, health condition, depression history, and other depression-related factors. Victor et al (28) developed a deep learning model to detect depression (measured with Patient Health Questionnaire-9) based on video questions regarding current mental well-being and demographics data.…”