Evidence for Mental Health Contributions to Medical Care in Diabetes Management: Economic and Professional Considerations

Comorbid depression and anxiety and their association with health care resource utilization among individuals with type 1 diabetes in the United States

BACKGROUND

Type 1 diabetes mellitus (T1DM) is a prevalent chronic endocrine disorder and accounts for 5%-10% of all diabetes cases worldwide. T1DM can have a substantial impact on health care utilization. Although it is well known that individuals with diabetes are at a greater risk of mental health disorders, specific evidence addressing the health care burden of comorbid depression/anxiety in people affected by T1DM is lacking.

OBJECTIVE

To assess health care resource utilization (HCRU) among adults with T1DM and comorbid depression or anxiety.

METHODS

We identified individuals aged 18 to 64 with a T1DM diagnosis from January 1, 2017, to December 31, 2021, using a 25% random sample of the IQVIA PharMetrics Plus for Academics database. The index date was the date of the first medical claim with a T1DM diagnosis. Eligibility required continuous medical and prescription coverage for 12 months before (baseline) and after (follow-up) the index date. Comorbid depression/anxiety and baseline characteristics were assessed during the baseline period. The following 2 mutually exclusive groups were created: individuals with T1DM and comorbid depression/anxiety, and those with only T1DM. To balance baseline demographic and clinical characteristics between the groups, we implemented 1:1 propensity-score matching. We assessed all-cause, diabetes-related, and major adverse cardiovascular event-related HCRU during the follow-up period. Logistic (binary) and negative binomial (count) regression models examined the association between comorbid depression/anxiety and HCRU across types of health care settings.

RESULTS

Out of 6,491 eligible individuals with T1DM, 1,168 (18%) had either depression or anxiety. In the matched cohort of 2,314 individuals, those with T1DM and comorbid depression/anxiety had significantly higher odds of all-cause emergency department visits (odds ratio = 1.67; 95% CI = 1.39-2.00) and higher rates of physician office visits (incidence rate ratio = 1.37; 95% CI = 1.27-1.47) and other outpatient encounters (incidence rate ratio = 1.23; 95% CI = 1.13-1.34) than those with only T1DM. Findings were similar for diabetes-related and major adverse cardiovascular event-related HCRU.

CONCLUSIONS

Comorbid depression/anxiety among individuals with T1DM results in significantly higher HCRU than T1DM alone. The findings underscore the importance of effective management of comorbid depression/anxiety in the T1DM population.

Proactive Identification of Patients with Diabetes at Risk of Uncontrolled Outcomes during a Diabetes Management Program: Conceptualization and Development Study Using Machine Learning

BACKGROUND

The growth in the capabilities of telehealth have made it possible to identify individuals with a higher risk of uncontrolled diabetes and provide them with targeted support and resources to help them manage their condition. Thus, predictive modeling has emerged as a valuable tool for the advancement of diabetes management.

OBJECTIVE

This study aimed to conceptualize and develop a novel machine learning (ML) approach to proactively identify participants enrolled in a remote diabetes monitoring program (RDMP) who were at risk of uncontrolled diabetes at 12 months in the program.

METHODS

Registry data from the Livongo for Diabetes RDMP were used to design separate dynamic predictive ML models to predict participant outcomes at each monthly checkpoint of the participants' program journey (month-n models) from the first day of onboarding (month-0 model) up to the 11th month (month-11 model). A participant's program journey began upon onboarding into the RDMP and monitoring their own blood glucose (BG) levels through the RDMP-provided BG meter. Each participant passed through 12 predicative models through their first year enrolled in the RDMP. Four categories of participant attributes (ie, survey data, BG data, medication fills, and health signals) were used for feature construction. The models were trained using the light gradient boosting machine and underwent hyperparameter tuning. The performance of the models was evaluated using standard metrics, including precision, recall, specificity, the area under the curve, the F1-score, and accuracy.

RESULTS

The ML models exhibited strong performance, accurately identifying observable at-risk participants, with recall ranging from 70% to 94% and precision from 40% to 88% across the 12-month program journey. Unobservable at-risk participants also showed promising performance, with recall ranging from 61% to 82% and precision from 42% to 61%. Overall, model performance improved as participants progressed through their program journey, demonstrating the importance of engagement data in predicting long-term clinical outcomes.

CONCLUSIONS

This study explored the Livongo for Diabetes RDMP participants' temporal and static attributes, identification of diabetes management patterns and characteristics, and their relationship to predict diabetes management outcomes. Proactive targeting ML models accurately identified participants at risk of uncontrolled diabetes with a high level of precision that was generalizable through future years within the RDMP. The ability to identify participants who are at risk at various time points throughout the program journey allows for personalized interventions to improve outcomes. This approach offers significant advancements in the feasibility of large-scale implementation in remote monitoring programs and can help prevent uncontrolled glycemic levels and diabetes-related complications. Future research should include the impact of significant changes that can affect a participant's diabetes management.

Patient and Provider Views on Psychosocial Screening in a Comprehensive Diabetes Center

Guidelines recommend routinely screening adults with diabetes for psychological concerns, but few diabetes clinics have adopted screening procedures. This study assessed patient and provider perspectives regarding the role of mental health in diabetes care, psychosocial screening procedures, and patients’ support needs. Patients with diabetes (n = 15; 73.3% type 2) and their medical providers (n = 11) participated in qualitative interviews. Thematic content analysis was used to categorize results. Participants believed that mental health was important to address within comprehensive diabetes care. Patients expressed positive or neutral opinions about psychosocial screening. Providers had mixed reactions; many thought that screening would be too time-consuming. Both groups emphasized that screening must include referral procedures to direct patients to mental health services. Patients and providers interviewed in this study viewed psychosocial screening as compatible with diabetes care. Including a mental health professional on the treatment team could reduce potential burden on other team members.