Targeting weight loss interventions to reduce cardiovascular complications of type 2 diabetes: a machine learning-based post-hoc analysis of heterogeneous treatment effects in the Look AHEAD trial

Abstract

Summary Background The Action for Health in Diabetes (Look AHEAD) trial investigated whether long-term cardiovascular disease morbidity and mortality could be reduced through a weight loss intervention among people with type 2 diabetes. Despite finding no significant reduction in cardiovascular events on average, it is possible that some subpopulations might have derived benefit. In this post-hoc analysis, we test the hypothesis that the overall neutral average treatment effect in the trial masked important heterogeneous treatment effects (HTEs) from intensive weight loss interventions. Methods We used causal forest modelling, which identifies HTEs, using a random half of the trial data (the training set). We applied Cox proportional hazards models to test the potential HTEs on the remaining half of the data (the testing set). The analysis was deemed exempt from review by the Columbia University Institutional Review Board, Protocol ID# AAAO3003. Findings Between Aug 22, 2001, and April 30, 2004, 5145 patients with type 2 diabetes were enrolled in the Look AHEAD randomised controlled trial, of whom 4901 were included in the The National Institute of Diabetes and Digestive and Kidney Diseases Repository and included in our analyses: 2450 for model development and 2451 in the testing dataset. Baseline HbA1c and self-reported general health distinguished participants who differentially benefited from the intervention. Cox models for the primary composite cardiovascular outcome revealed a number needed to treat of 28·9 to prevent 1 event over 9·6 years among participants with HbA1c 6·8% or higher, or both HbA1c less than 6·8% and Short Form Health Survey (SF-36) general health score of 48 or more (2101 [86%] of 2451 participants in the testing dataset; 167 [16%] of 1046 primary outcome events for intervention vs 205 [19%] of 1055 for control, absolute risk reduction of 3·46%, 95% CI 0·21–6·73%, p=0·038) By contrast, participants with HbA1c less than 6·8% and baseline SF-36 general health score of less than 48 (350 [14%] of 2451 participants in the testing data; 27 [16%] of 171 primary outcome events for intervention vs 15 [8%] of 179 primary outcome events for control) had an absolute risk increase of the primary outcome of 7·41% (0·60 to 14·22, p=0·003). Interpretation Look AHEAD participants with moderately or poorly controlled diabetes (HbA1c 6·8% or higher) and subjects with well controlled diabetes (HbA1c less than 6·8%) and good self-reported health (85% of the overall study population) averted cardiovascular events from a behavioural intervention aimed at weight loss. However, 15% of participants with well controlled diabetes and poor self-reported general health experienced negative effects that rendered the overall study outcome neutral. HbA1c and a short questionnaire on general health might identify people with type 2 diabetes likely to derive benefit from an intensive lifestyle intervention aimed at weight loss. Funding None.

7. Obesity Management for the Treatment of Type 2 Diabetes:Standards of Medical Care in Diabetes—2018

“…A post hoc analysis of the Look AHEAD study suggests that heterogeneous treatment effects may have been present. Participants who had moderately or poorly controlled diabetes (A1C 6.8% or higher) as well as both those with well-controlled diabetes (A1C less than 6.8%) and good self-reported health were found to have significantly reduced cardiovascular events with intensive lifestyle intervention during follow-up (18).…”

Multidisciplinary lifestyle management approach in patients with type 2 diabetes mellitus in real clinical practice. Results of application “Life is easy” programme in Russia

“…Такой эффект исследователи связывают с тем, что у этих 15% участников была низкая комплаентность, а также исходно отрицательное восприятие своего состояния здоровья, что сильно коррелировало с самооценкой психического здоровья и депрессией. Это свидетельствует о том, что психоэмоциональные факторы могут влиять на эффективность мероприятий по изменению образа жизни [25]. Это, наряду с необходимостью контроля питания и активного образа жизни, демонстрирует важность персонализированного психологического подхода к пациенту с целью повышения мотивации, готовности и приверженности пациентов к изменению образа жизни.…”

Identifying treatment effects of an informal caregiver education intervention to increase days in the community and decrease caregiver distress: a machine-learning secondary analysis of subgroup effects in the HI-FIVES randomized clinical trial

“…Our study also highlights the challenges of applying machine learning to health services research, in general, and to post-hoc analyses of clinical trials, in particular [23,46]. There are notable limitations both in the methods and in the programs available to implement the methods.…”

“…This is a major challenge for post-hoc analyses of trial data because most intervention trials in health care have relatively small samples. The work that has been done to date to apply machine learning to trial data has taken advantage of large health trials [23,46]. To address this challenge with our small sample we examined the consistency across folds of our dataset; our trees were consistent.…”

“…In addition, this approach avoids multiple testing errors by building a decision tree through iteratively partitioning a space that comprises multiple covariates. In contrast, standard variable by variable interaction methods are only able to partition the space of one covariate at a time which increases multiple testing error when analysts need to examine multiple potential moderators [23].…”