Q-Finder: An Algorithm for Credible Subgroup Discovery in Clinical Data Analysis — An Application to the International Diabetes Management Practice Study

Abstract

Addressing the heterogeneity of both the outcome of a disease and the treatment response to an intervention is a mandatory pathway for regulatory approval of medicines. In randomized clinical trials (RCTs), confirmatory subgroup analyses focus on the assessment of drugs in predefined subgroups, while exploratory ones allow a posteriori the identification of subsets of patients who respond differently. Within the latter area, subgroup discovery (SD) data mining approach is widely used—particularly in precision medicine—to evaluate treatment effect across different groups of patients from various data sources (be it from clinical trials or real-world data). However, both the limited consideration by standard SD algorithms of recommended criteria to define credible subgroups and the lack of statistical power of the findings after correcting for multiple testing hinder the generation of hypothesis and their acceptance by healthcare authorities and practitioners. In this paper, we present the Q-Finder algorithm that aims to generate statistically credible subgroups to answer clinical questions, such as finding drivers of natural disease progression or treatment response. It combines an exhaustive search with a cascade of filters based on metrics assessing key credibility criteria, including relative risk reduction assessment, adjustment on confounding factors, individual feature’s contribution to the subgroup’s effect, interaction tests for assessing between-subgroup treatment effect interactions and tests adjustment (multiple testing). This allows Q-Finder to directly target and assess subgroups on recommended credibility criteria. The top-k credible subgroups are then selected, while accounting for subgroups’ diversity and, possibly, clinical relevance. Those subgroups are tested on independent data to assess their consistency across databases, while preserving statistical power by limiting the number of tests. To illustrate this algorithm, we applied it on the database of the International Diabetes Management Practice Study (IDMPS) to better understand the drivers of improved glycemic control and rate of episodes of hypoglycemia in type 2 diabetics patients. We compared Q-Finder with state-of-the-art approaches from both Subgroup Identification and Knowledge Discovery in Databases literature. The results demonstrate its ability to identify and support a short list of highly credible and diverse data-driven subgroups for both prognostic and predictive tasks.

Qluster: An Easy-to-Implement Generic Workflow for Robust Clustering of Health Data

“…In the field of Machine Learning, clustering methods pertain to the so-called unsupervised learning methods. Clustering should not be confused with the field of Subgroup Discovery, which also aims at finding groups but in a supervised way, for example to identify prognostic factors of an outcome or predictive factors of the treatment effect on an outcome (Esnault et al 2020;Zhou et al 2019). The many clustering algorithms that exist in the literature (Fahad et al 2014 ;Ahmad et al 2019;Xu et al 2010) can be classified according to the cluster models (centroid, connectivity, group, distribution, density, graph, etc.).…”

Qluster: An Easy-to-Implement Generic Workflow for Robust Clustering of Health Data

“…In the field of Machine Learning, clustering methods pertain to the so-called unsupervised learning methods. Clustering should not be confused with the field of Subgroup Discovery, which also aims at finding groups but in a supervised way, for example to identify prognostic factors of an outcome or predictive factors of the treatment effect on an outcome (Esnault et al 2020;Zhou et al 2019). The many clustering algorithms that exist in the literature (e.g.…”

Identification of predictive factors of diabetic ketoacidosis in type 1 diabetes using a subgroup discovery algorithm

“…The analysis was performed using Q-Finder (Quinten, Paris, France), a supervised non-parametric proprietary subgroup discovery algorithm, for which detailed methodology and algorithm principles have been described previously. 11 Prior to initiating the analysis, the full dataset was divided into a learning dataset (50%), test dataset (25%) and validation dataset (25%). The datasets were created by random sampling, stratified by DKA, age, gender, migration background (defined as a patient, or at least one parent of the patient, born outside of Germany, Austria, Switzerland or Luxembourg), HbA1c and follow-up duration variables.…”

“…Advanced analytics can supplement the conventional statistics described above to generate new insights on DKA risk factors using large diabetes cohorts such as the DPV. Q‐Finder (Quinten, Paris, France) is a subgroup discovery algorithm that identifies patient profiles associated with an outcome of interest and the specific combinations of distinct characteristics for each profile 9–11 . The objective of this study was to identify predictive factors for DKA in type 1 diabetes by conducting a retrospective analysis of data from the DPV using a novel analytical approach leveraging the Q‐Finder algorithm.…”