Towards Outcome-Driven Patient Subgroups: A Machine Learning Analysis Across Six Depression Treatment Studies

Artificial Intelligence in Depression – Medication Enhancement (AID-ME): A Cluster Randomized Trial of a Deep Learning Enabled Clinical Decision Support System for Personalized Depression Treatment Selection and Management

“…This occurred despite best efforts to recruit primary care providers, which proved to be di cult due several factors (lack of embedded research staff, time-consuming clinic-level onboarding in busy clinical practices, and primary care service adaptation to the post COVID-19 environment). However, previous work has shown that the CDSS is feasible in primary care 19 , 18 , and AI training data included patients in both primary and specialized services 22 . Given that the majority of MDD is treated by primary care physicians, and that patients in primary care are more likely to have less treatment resistant or recurrent depression, future work will need to con rm similar if not improved results in primary care 27 .…”

“…Extensive feasibility and ease of use testing of this CDSS was previously performed in both simulation center and in vivo feasibility studies [16][17][18][19] . With in silico testing demonstrating that the AI component should help improve remission rates 6, [20][21][22] and in vivo testing demonstrating that the platform was feasible, easy to use and likely safe [16][17][18][19] the current study was undertaken with the main objective of determining the e cacy of the platform in improving depression treatment outcomes in patients with moderate to severe depression, as well as to assess platform safety.…”

Development and Validation of a Deep-Learning Model for Differential Treatment Benefit Prediction for Adults with Major Depressive Disorder Deployed in the Artificial Intelligence in Depression – Medication Enhancement (AID-ME) Study

“…On the other hand, data contained within electronic medical records requires that modelers contend with the biases inherent in observational data 16,17 as well as, in many cases, the lack of clear outcome measures.These limitations have likely hindered the development and deployment of machine learning models into real clinical environments 8,17 . In previous work, we have demonstrated deep learning models which can perform differential treatment bene t prediction for more than two treatments and which are predicted to improve population remission rates 7,18,19 . We have also demonstrated methods for assessing model bias and for unifying clinical trial datasets in order to enable model training 8,19 .…”

“…In previous work, we have demonstrated deep learning models which can perform differential treatment bene t prediction for more than two treatments and which are predicted to improve population remission rates 7,18,19 . We have also demonstrated methods for assessing model bias and for unifying clinical trial datasets in order to enable model training 8,19 . Finally, we have implemented versions of these models in simulation center and in-clinic feasibility studies in order to determine if clinicians and patients are accepting of these models, if they are easy to use in clinical practice, and if they are perceived by clinicians and patients to offer a clinical bene t 14,15,20,21 .…”