Predicting individual treatment effects with machine learning in IMPACT

Predicting individual treatment effects with machine learning in IMPACT

With the constant increase in computational power and the rise of big data, artificial intelligence (AI) is rapidly moving forward and is currently invading different domains of healthcare. The central idea of the project is to use machine learning approaches to detect patterns between several baseline patient characteristics, interventions and particular outcomes of Randomized Controlled Trials (RCT). The advantage of machine learning, compared to the classical statistical models, is the ability to learn more complex patterns in the data without many assumptions about underlying distributions. At this stage, RCT are providing the highest level of evidence on the efficacy of any pharmaceutical intervention. These trials are absolutely needed in product development and obligatory in different phases before any drug will be considered by health authorities for reimbursement and broad clinical use.In RCT, the current statistical approaches are comparing groups and subgroups in terms of different predefined outcomes. These approaches are highly important to demonstrate the efficacy or futility of an intervention on group level. For a clinician in daily practice, treatment decisions must be made on individual level. However, it is still hard to predict if an individual patient will be a responder or non-responder to an intervention based on group evidence of its RCT. Machine learning models may overcome this problem by looking at the likelihood an individual is going to respond on a studied intervention. By learning from relationships in a detailed training data set, intelligent algorithms will be developed to predict probabilities of outcomes on an individual patient level.This project will focus on the InforMing the Pathway of COPD Treatment (IMPACT) dataset in the domain of Chronic Obstructive Pulmonary Diseases (COPD). COPD is most often caused by smoking and is currently the 3rd leading cause of mortality worldwide (after cardiovascular disease and cancer). Different treatments via inhalers or oral drug intakes have been validated by large randomized controlled trials and are currently being used in daily practice. Unfortunately, many of the patients taking these medications daily, are not responding to the drug that has been prescribed to them. This is caused by the high heterogeneity and the complexity of the disease that is not yet well-understood. Some subgroups may respond better to the treatment while other subgroups of the disease do not respond at all. Intelligent tools that can identify responders from non-responders in advance, are therefore of utmost importance, not only from the individual perspective but also from a health-economic perspective.The objective of our research is to develop machine learning-based models to predict individual treatment effects and to compare the developed strategies with currently applied regression models. While the concept of individual treatment effect might be clear and obvious, assessing or estimating it is highly challenging, and impossible for classical statistical methods. Individual subjects are only randomized to one intervention arm, so either the effect with or the effect without treatment can be estimated and never the exact treatment effect (difference). As such, machine learning models need to be developed and tuned to overcome this problem of causal inference. Different sets of baseline features will be used to augment prediction power at minimal redundancy and post-hoc machine learning tools will be used to identify key input features for prediction power. Training and validation data sets will be used to develop a generic approache to allow fast evaluation of other - similar pharma trials. Subsequently, cloud-based software tools may be developed to allow clinicians to predict therapeutic responses. As such, artificial intelligence may be at the doorstep of personalized medicine in chronic respiratory diseases.

[{ "PostingID": 16073, "Title": "GSK-CTT116855", "Description": "A phase III, 52 week, randomized, double-blind, 3-arm parallel group study, comparing the efficacy, safety and tolerability of the fixed dose triple combination FF/UMEC/VI with the fixed dose dual combinations of FF/VI and UMEC/VI, all administered once-daily in the morning via a dry powder inhaler in subjects with chronic obstructive pulmonary disease" }]