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

Identification of profiles associated with conversions between the Alzheimer's disease stages, using a machine learning approach

BACKGROUND

The identification of factors involved in the conversion across the different Alzheimer's disease (AD) stages is crucial to prevent or slow the disease progression. We aimed to assess the factors and their combination associated with the conversion across the AD stages, from mild cognitive impairment to dementia, at a mild, moderate or severe stage and to identify profiles associated with earliest/latest conversion across the AD stages.

METHODS

In this study conducted on the real-life MEMORA cohort data collected from January 1, 2013, and December 31, 2019, three cohorts were selected depending on the baseline neurocognitive stage from a consecutive sample of patients attending a memory center, aged between 50 and 90 years old, with a diagnosis of AD during the follow-up, and with at least 2 visits at 6 months to 1 year of interval. A machine learning approach was used to assess the relationship between factors including socio-demographic characteristics, comorbidities and history of diseases, prescription of drugs, and geriatric hospitalizations, and the censored time to conversion from mild cognitive impairment to AD dementia, from the mild stage of dementia to the moderate or severe stages of AD dementia, and from the moderate stage of AD dementia to the severe stage. Profiles of earliest/latest conversion compared to median time to conversion across stages were identified. The median time to conversion was estimated with a Kaplan-Meier estimator.

RESULTS

Overall, 2891 patients were included (mean age 77±9 years old, 65% women). The median time of follow-up was 28 months for mild cognitive impairment (MCI) patients, 33 months for mild AD dementia and 30 months for moderate AD dementia. Among the 1264 patients at MCI stage, 61% converted to AD dementia (median time to conversion: 25 months). Among the 1142 patients with mild AD dementia, 59% converted to moderate/severe stage (median time: 23 months) and among the 1332 patients with moderate AD dementia, 23% converted to severe stage (Q3 time to conversion: 22 months). Among the studied factors, cardiovascular comorbidities, anxiety, social isolation, osteoporosis, and hearing disorders were identified as being associated with earlier conversion across stages. Symptomatic treatment i.e. cholinesterase inhibitors for AD was associated with later conversion from mild stage of dementia to moderate/severe stages.

CONCLUSION

This study based on a machine learning approach allowed to identify potentially modifiable factors associated with conversion across AD stages for which timely interventions may be implemented to delay disease progression.

Surprising and novel multivariate sequential patterns using odds ratio for temporal evolution in healthcare

BACKGROUND

Pattern mining techniques are helpful tools when extracting new knowledge in real practice, but the overwhelming number of patterns is still a limiting factor in the health-care domain. Current efforts concerning the definition of measures of interest for patterns are focused on reducing the number of patterns and quantifying their relevance (utility/usefulness). However, although the temporal dimension plays a key role in medical records, few efforts have been made to extract temporal knowledge about the patient's evolution from multivariate sequential patterns.

METHODS

In this paper, we propose a method to extract a new type of patterns in the clinical domain called Jumping Diagnostic Odds Ratio Sequential Patterns (JDORSP). The aim of this method is to employ the odds ratio to identify a concise set of sequential patterns that represent a patient's state with a statistically significant protection factor (i.e., a pattern associated with patients that survive) and those extensions whose evolution suddenly changes the patient's clinical state, thus making the sequential patterns a statistically significant risk factor (i.e., a pattern associated with patients that do not survive), or vice versa.

RESULTS

The results of our experiments highlight that our method reduces the number of sequential patterns obtained with state-of-the-art pattern reduction methods by over 95%. Only by achieving this drastic reduction can medical experts carry out a comprehensive clinical evaluation of the patterns that might be considered medical knowledge regarding the temporal evolution of the patients. We have evaluated the surprisingness and relevance of the sequential patterns with clinicians, and the most interesting fact is the high surprisingness of the extensions of the patterns that become a protection factor, that is, the patients that recover after several days of being at high risk of dying.

CONCLUSIONS

Our proposed method with which to extract JDORSP generates a set of interpretable multivariate sequential patterns with new knowledge regarding the temporal evolution of the patients. The number of patterns is greatly reduced when compared to those generated by other methods and measures of interest. An additional advantage of this method is that it does not require any parameters or thresholds, and that the reduced number of patterns allows a manual evaluation.

Automated identification of patient subgroups: A case-study on mortality of COVID-19 patients admitted to the ICU

BACKGROUND

- Subgroup discovery (SGD) is the automated splitting of the data into complex subgroups. Various SGD methods have been applied to the medical domain, but none have been extensively evaluated. We assess the numerical and clinical quality of SGD methods.

METHOD

- We applied the improved Subgroup Set Discovery (SSD++), Patient Rule Induction Method (PRIM) and APRIORI - Subgroup Discovery (APRIORI-SD) algorithms to obtain patient subgroups on observational data of 14,548 COVID-19 patients admitted to 73 Dutch intensive care units. Hospital mortality was the clinical outcome. Numerical significance of the subgroups was assessed with information-theoretic measures. Clinical significance of the subgroups was assessed by comparing variable importance on population and subgroup levels and by expert evaluation.

RESULTS

- The tested algorithms varied widely in the total number of discovered subgroups (5-62), the number of selected variables, and the predictive value of the subgroups. Qualitative assessment showed that the found subgroups make clinical sense. SSD++ found most subgroups (n = 62), which added predictive value and generally showed high potential for clinical use. APRIORI-SD and PRIM found fewer subgroups (n = 5 and 6), which did not add predictive value and were clinically less relevant.

CONCLUSION

- Automated SGD methods find clinical subgroups that are relevant when assessed quantitatively (yield added predictive value) and qualitatively (intensivists consider the subgroups significant). Different methods yield different subgroups with varying degrees of predictive performance and clinical quality. External validation is needed to generalize the results to other populations and future research should explore which algorithm performs best in other settings.

Virtual patients, digital twins and causal disease models: paving the ground for in silico clinical trials

Computational models are being explored to simulate in silico the efficacy and safety of drug candidates and medical devices. Disease models that are based on patients' profiling data are being produced to represent interactomes of genes or proteins and to infer causality in the pathophysiology {AuQ: Edit OK?}, which makes it possible to mimic the impact of drugs on relevant targets. Virtual patients designed from medical records as well as digital twins were generated to simulate specific organs and to predict treatment efficacy at the individual patient level {AuQ: Edit OK?}. As the acceptance of digital evidence by regulators grows, predictive artificial intelligence (AI)-based models will support the design of confirmatory trials in humans and will accelerate the development of efficient drugs and medical devices.

Qluster: An easy-to-implement generic workflow for robust clustering of health data

The exploration of heath data by clustering algorithms allows to better describe the populations of interest by seeking the sub-profiles that compose it. This therefore reinforces medical knowledge, whether it is about a disease or a targeted population in real life. Nevertheless, contrary to the so-called conventional biostatistical methods where numerous guidelines exist, the standardization of data science approaches in clinical research remains a little discussed subject. This results in a significant variability in the execution of data science projects, whether in terms of algorithms used, reliability and credibility of the designed approach. Taking the path of parsimonious and judicious choice of both algorithms and implementations at each stage, this article proposes Qluster, a practical workflow for performing clustering tasks. Indeed, this workflow makes a compromise between (1) genericity of applications (e.g. usable on small or big data, on continuous, categorical or mixed variables, on database of high-dimensionality or not), (2) ease of implementation (need for few packages, few algorithms, few parameters, ...), and (3) robustness (e.g. use of proven algorithms and robust packages, evaluation of the stability of clusters, management of noise and multicollinearity). This workflow can be easily automated and/or routinely applied on a wide range of clustering projects. It can be useful both for data scientists with little experience in the field to make data clustering easier and more robust, and for more experienced data scientists who are looking for a straightforward and reliable solution to routinely perform preliminary data mining. A synthesis of the literature on data clustering as well as the scientific rationale supporting the proposed workflow is also provided. Finally, a detailed application of the workflow on a concrete use case is provided, along with a practical discussion for data scientists. An implementation on the Dataiku platform is available upon request to the authors.