Identification of subgroups of patients with type 2 diabetes with differences in renal function preservation, comparing patients receiving sodium-glucose co-transporter-2 inhibitors with those receiving dipeptidyl peptidase-4 inhibitors, using a supervised machine-learning algorithm (PROFILE study): A retrospective analysis of a Japanese commercial medical database

The association between sodium glucose cotransporter-2 inhibitors vs dipeptidyl peptidase-4 inhibitors and renal outcomes in people discharged from hospital with type 2 diabetes: A population-based cohort study

BACKGROUND

We investigated the association between post-hospital discharge use of sodium glucose cotransporter-2 inhibitors (SGLT-2is) compared to dipeptidyl peptidase-4 inhibitors (DPP-4is) and the incidence of hospitalization for acute renal failure (ARF) and chronic kidney disease (CKD) in people with type 2 diabetes.

METHODS

We conducted a retrospective cohort study using linked hospital and prescription data. Our cohort included people aged ≥30 years with type 2 diabetes discharged from a hospital in Victoria, Australia, from December 2013 to June 2018. We compared new users of SGLT-2is with new users of DPP-4is following discharge. People were followed from first dispensing of a SGLT-2i or DPP-4i to a subsequent hospital admission for ARF or CKD. We used competing risk models with inverse probability of treatment weighting (IPTW) to estimate subhazard ratios.

RESULTS

In total, 9620 people initiated SGLT-2is and 9962 initiated DPP-4is. The incidence rate of ARF was 12.3 per 1000 person-years (median years of follow-up [interquartile range [IQR] 1.4 [0.7-2.2]) among SGLT-2i initiators and 18.9 per 1000 person-years (median years of follow-up [IQR] 1.7 [0.8-2.6]) among DPP-4i initiators (adjusted subhazard ratio with IPTW 0.78; 95% confidence interval [CI] 0.70-0.86). The incidence rate of CKD was 6.0 per 1000 person-years (median years of follow-up [IQR] 1.4 [0.7-2.2]) among SGLT-2i initiators and 8.9 per 1000 person-years (median years of follow-up [IQR] 1.7 [0.8-2.6]) among DPP-4i initiators (adjusted subhazard ratio with IPTW 0.83; 95% CI 0.73-0.94).

CONCLUSIONS

Real-world data support using SGLT-2is over DPP-4is for preventing acute and chronic renal events in people with type 2 diabetes.

Treatment effect heterogeneity following type 2 diabetes treatment with GLP1-receptor agonists and SGLT2-inhibitors: a systematic review

BACKGROUND

A precision medicine approach in type 2 diabetes requires the identification of clinical and biological features that are reproducibly associated with differences in clinical outcomes with specific anti-hyperglycaemic therapies. Robust evidence of such treatment effect heterogeneity could support more individualized clinical decisions on optimal type 2 diabetes therapy.

METHODS

We performed a pre-registered systematic review of meta-analysis studies, randomized control trials, and observational studies evaluating clinical and biological features associated with heterogenous treatment effects for SGLT2-inhibitor and GLP1-receptor agonist therapies, considering glycaemic, cardiovascular, and renal outcomes. After screening 5,686 studies, we included 101 studies of SGLT2-inhibitors and 75 studies of GLP1-receptor agonists in the final systematic review.

RESULTS

Here we show that the majority of included papers have methodological limitations precluding robust assessment of treatment effect heterogeneity. For SGLT2-inhibitors, multiple observational studies suggest lower renal function as a predictor of lesser glycaemic response, while markers of reduced insulin secretion predict lesser glycaemic response with GLP1-receptor agonists. For both therapies, multiple post-hoc analyses of randomized control trials (including trial meta-analysis) identify minimal clinically relevant treatment effect heterogeneity for cardiovascular and renal outcomes.

CONCLUSIONS

Current evidence on treatment effect heterogeneity for SGLT2-inhibitor and GLP1-receptor agonist therapies is limited, likely reflecting the methodological limitations of published studies. Robust and appropriately powered studies are required to understand type 2 diabetes treatment effect heterogeneity and evaluate the potential for precision medicine to inform future clinical care.

Precision medicine in type 2 diabetes: A systematic review of treatment effect heterogeneity for GLP1-receptor agonists and SGLT2-inhibitors

Background

A precision medicine approach in type 2 diabetes requires identification of clinical and biological features that are reproducibly associated with differences in clinical outcomes with specific anti-hyperglycaemic therapies. Robust evidence of such treatment effect heterogeneity could support more individualized clinical decisions on optimal type 2 diabetes therapy.

Methods

We performed a pre-registered systematic review of meta-analysis studies, randomized control trials, and observational studies evaluating clinical and biological features associated with heterogenous treatment effects for SGLT2-inhibitor and GLP1-receptor agonist therapies, considering glycaemic, cardiovascular, and renal outcomes.

Results

After screening 5,686 studies, we included 101 studies of SGLT2-inhibitors and 75 studies of GLP1-receptor agonists in the final systematic review. The majority of papers had methodological limitations precluding robust assessment of treatment effect heterogeneity. For glycaemic outcomes, most cohorts were observational, with multiple analyses identifying lower renal function as a predictor of lesser glycaemic response with SGLT2-inhibitors and markers of reduced insulin secretion as predictors of lesser response with GLP1-receptor agonists. For cardiovascular and renal outcomes, the majority of included studies were post-hoc analyses of randomized control trials (including meta-analysis studies) which identified limited clinically relevant treatment effect heterogeneity.

Conclusions

Current evidence on treatment effect heterogeneity for SGLT2-inhibitor and GLP1-receptor agonist therapies is limited, likely reflecting the methodological limitations of published studies. Robust and appropriately powered studies are required to understand type 2 diabetes treatment effect heterogeneity and evaluate the potential for precision medicine to inform future clinical care.

Plain language summary

This review identifies research that helps understand which clinical and biological factors that are associated with different outcomes for specific type 2 diabetes treatments. This information could help clinical providers and patients make better informed personalized decisions about type 2 diabetes treatments. We focused on two common type 2 diabetes treatments: SGLT2-inhibitors and GLP1-receptor agonists, and three outcomes: blood glucose control, heart disease, and kidney disease. We identified some potential factors that are likely to lessen blood glucose control including lower kidney function for SGLT2-inhibitors and lower insulin secretion for GLP1-receptor agonists. We did not identify clear factors that alter heart and renal disease outcomes for either treatment. Most of the studies had limitations, meaning more research is needed to fully understand the factors that influence treatment outcomes in type 2 diabetes.

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.

Review: Machine learning in precision pharmacotherapy of type 2 diabetes-A promising future or a glimpse of hope?

Precision pharmacotherapy of diabetes requires judicious selection of the optimal therapeutic agent for individual patients. Artificial intelligence (AI), a swiftly expanding discipline, holds substantial potential to transform current practices in diabetes diagnosis and management. This manuscript provides a comprehensive review of contemporary research investigating drug responses in patient subgroups, stratified via either supervised or unsupervised machine learning approaches. The prevalent algorithmic workflow for investigating drug responses using machine learning involves cohort selection, data processing, predictor selection, development and validation of machine learning methods, subgroup allocation, and subsequent analysis of drug response. Despite the promising feature, current research does not yet provide sufficient evidence to implement machine learning algorithms into routine clinical practice, due to a lack of simplicity, validation, or demonstrated efficacy. Nevertheless, we anticipate that the evolving evidence base will increasingly substantiate the role of machine learning in molding precision pharmacotherapy for diabetes.

The accuracy versus interpretability trade-off in fraud detection model

Like a hydra, fraudsters adapt and circumvent increasingly sophisticated barriers erected by public or private institutions. Among these institutions, banks must quickly take measures to avoid losses while guaranteeing the satisfaction of law-abiding customers. Facing an expanding flow of operations, effective banking relies on data analytics to support established risk control processes, but also on a better understanding of the underlying fraud mechanism. In addition, fraud being a criminal offence, the evidential aspect of the process must also be considered. These legal, operational, and strategic constraints lead to compromises on the means to be implemented for fraud management. This paper first focuses on the translation of practical questions raised in the banking industry at each step of the fraud management process into performance evaluation required to design a fraud detection model. Secondly, it considers a range of machine learning approaches that address these specificities: the imbalance between fraudulent and nonfraudulent operations, the lack of fully trusted labels, the concept-drift phenomenon, and the unavoidable trade-off between accuracy and interpretability of detection. This state-of-the-art review sheds some light on a technology race between black box machine learning models improved by post-hoc interpretation and intrinsic interpretable models boosted to gain accuracy. Finally, it discusses how concrete and promising hybrid approaches can provide pragmatic, short-term answers to banks and policy makers without swallowing up stakeholders with economical and ethical stakes in this technological race.

What Have We Learned so Far From the Use of Sodium-Glucose Cotransporter 2 Inhibitors in Clinical Practice?

Since the introduction of sodium-glucose cotransporter 2 (SGLT2) inhibitors, the aim of this therapy has expanded from being solely a glucose-lowering treatment into also being organ protective even in people without diabetes. In this review, we present this evolution of the treatment principle, from early studies over randomized controlled trials. We discuss available real-world evidence and summarize a number of recent post hoc analyses from the randomized controlled trials with kidney end points. As the use of sodium-glucose cotransporter 2 inhibitors becomes more widespread, new questions arise regarding initiation and follow-up, which we try to answer by providing the currently available data. For translation of study results to global effects, implementation becomes important. As is often the case, this does not happen without barriers, which must be addressed and handled. Finally, future studies and populations are discussed because it may well be that sodium-glucose cotransporter 2 inhibition are expanding into further areas.

Current trends in diabetes mellitus database research in Japan

With the widespread use of electronic medical records and administrative claims databases, analytic results from so-called real-world data have become increasingly important in healthcare decision-making. Diabetes mellitus is a heterogeneous condition that involves a broad spectrum of patients. Real-world database studies have been recognised as a powerful tool to understand the impact of current practices on clinical courses and outcomes, such as long-term glucose control, development of microvascular or macro-vascular diseases, and mortality. Diabetes is also a major global health issue and poses a significant social and economic burden worldwide. Therefore, it is critical to understand the epidemiology, clinical course, treatment reality, and long-term outcomes of diabetes to determine realistic solutions to a variety of disease-related issues that we are facing. In the present review, we summarise the healthcare system and large-scale databases currently available in Japan, introduce the results from recent database studies involving Japanese patients with diabetes, and discuss future opportunities and challenges for the use of databases in the management of diabetes.

Patient journey through cases of depression from claims database using machine learning algorithms

Health insurance and acute hospital-based claims have recently become available as real-world data after marketing in Japan and, thus, classification and prediction using the machine learning approach can be applied to them. However, the methodology used for the analysis of real-world data has been hitherto under debate and research on visualizing the patient journey is still inconclusive. So far, to classify diseases based on medical histories and patient demographic background and to predict the patient prognosis for each disease, the correlation structure of real-world data has been estimated by machine learning. Therefore, we applied association analysis to real-world data to consider a combination of disease events as the patient journey for depression diagnoses. However, association analysis makes it difficult to interpret multiple outcome measures simultaneously and comprehensively. To address this issue, we applied the Topological Data Analysis (TDA) Mapper to sequentially interpret multiple indices, thus obtaining a visual classification of the diseases commonly associated with depression. Under this approach, the visual and continuous classification of related diseases may contribute to precision medicine research and can help pharmaceutical companies provide appropriate personalized medical care.

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

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.

Social deprivation aggravates post-operative morbidity in carcinologic colorectal surgery: Results of the COINCIDE multicenter study

AIM OF THE STUDY

Evaluate the impact of social deprivation on morbidity and mortality in surgery for colorectal cancer.

METHODS

The COINCIDE prospective cohort included nearly 2,000 consecutive patients operated on for colorectal cancer at the Assistance Publique-Hospitals of Paris (AP-HP) from 2008 to 2010. The data on these patients were crossed with the PMSI administrative database. The European Social Deprivation Index (EDI) was calculated for each patient and classified into five quintiles (quintiles 4 and 5 being the most disadvantaged patients). Thirty-day post-operative morbidity was determined according to the Dindo-Clavien classification, with a Had®Hoc re-analysis of each file. Statistical analysis was performed using the proprietary Q-finder® algorithm.

RESULTS

One thousand two hundred and fifty nine curative colorectal resections were analyzed. Mortality was 2.7% and severe morbidity (Dindo-Clavien≥3) occurred in 16.4%. Mortality was not statistically significantly increased among the most disadvantaged who made up almost two thirds of the population (64.2%). Patients in quintiles 4 and 5 had a statistically significant increase in severe morbidity. The relative risk remained 1.5 even after adjustment for the known risk factors found in the analysis: age>70 years, ASA score, urgency, and laparotomy.

CONCLUSIONS

The EDI represents an independent risk factor for severe morbidity after carcinologic colorectal resection. This study suggests that the determinants of health are multidimensional and do not depend solely on the quality and performance of the care system. The inclusion of this index in our surgical databases is therefore necessary, as is its use in health policy for the distribution of resources.

Rationale and methodology for a European pooled analysis of postmarketing interventional and observational studies of insulin glargine 300 U/mL in diabetes: protocol of REALI project

INTRODUCTION

Type 2 diabetes mellitus (T2DM) is a common and heterogeneous disease. Using advanced analytic approaches to explore real-world data may identify different disease characteristics, responses to treatment and progression patterns. Insulin glargine 300 units/mL (Gla-300) is a second-generation basal insulin analogue with preserved glucose-lowering efficacy but reduced risk of hypoglycaemia. The purpose of the REALI pooled analysis described in this paper is to advance the understanding of the effectiveness and real-world safety of Gla-300 based on a large European patient database of postmarketing interventional and observational studies.

METHODS AND ANALYSIS

In the current round of pooling, REALI will include data from up to 10 000 subjects with diabetes mellitus (mostly T2DM) from 20 European countries. Outcomes of interest include change from baseline to week 24 in haemoglobin A_1c, fasting plasma glucose, self-measured plasma glucose, body weight, insulin dose, incidence and rate of any-time-of-the-day and nocturnal hypoglycaemia. The data pool is being investigated using two complementary methodologies: a conventional descriptive, univariate and multivariable prognostic analysis; and a data-mining approach using subgroup discovery to identify phenotypic clusters of patients who are highly associated with the outcome of interest. By mid-2019, deidentified data of 7584 patients were included in the REALI database, with a further expected increase in patient number in 2020 as a result of pooling additional studies.

ETHICS AND DISSEMINATION

The proposed study does not involve collection of primary data. Moreover, all individual study protocols were approved by independent local ethics committees, and all study participants provided written informed consent. Furthermore, patient data is deidentified before inclusion in the REALI database. Hence, there is no requirement for ethical approval. Results will be disseminated via peer-reviewed publications and presentations at international congresses as data are analysed.

What have we learned about renal protection from the cardiovascular outcome trials and observational analyses with SGLT2 inhibitors?

Over the past 5 years, sodium-glucose cotransport 2 (SGLT2) inhibitors have been increasingly regarded as glycaemic agents with cardiovascular (CV) and renal protective effects. The CV benefits of SGLT2 inhibitors have been well established in patients with type 2 diabetes (T2D) and a range of CV comorbidities at baseline. Subsequently, the renal benefits of SGLT2 inhibitors were established in the CREDENCE trial, a dedicated renal outcome trial where canagliflozin reduced the primary composite renal outcome by 30%. In light of these trials, clinical practice guidelines have rapidly evolved, recommending the use of SGLT2 inhibitors as renal and cardioprotective agents in appropriate patient populations. Accordingly, it is important to have an in-depth understanding of the evidence underlying the use of SGLT2 inhibitors in patients with T2D based on published clinical trials and real-world evidence (RWE) studies, as well as information related to potential safety concerns. To accomplish this, we reviewed the evidence for renal protection and safety with SGLT2 inhibitors in the EMPA-REG OUTCOME, CANVAS Program and DECLARE-TIMI 58 CV safety trials, and in the growing body of evidence emerging from real-world studies. This body of work has shown that SGLT2 inhibitors reduce the risk of surrogate renal endpoints such as albuminuria and mitigate the risk of hard renal endpoints including doubling of serum creatinine and end-stage kidney disease in patients with T2D.

The present and future scope of real-world evidence research in diabetes: What questions can and cannot be answered and what might be possible in the future?

The last decade has witnessed an exponential growth in the opportunities to collect and link health-related data from multiple resources, including primary care, administrative, and device data. The availability of these "real-world," "big data" has fuelled also an intense methodological research into methods to handle them and extract actionable information. In medicine, the evidence generated from "real-world data" (RWD), which are not purposely collected to answer biomedical questions, is commonly termed "real-world evidence" (RWE). In this review, we focus on RWD and RWE in the area of diabetes research, highlighting their contributions in the last decade; and give some suggestions for future RWE diabetes research, by applying well-established and less-known tools to direct RWE diabetes research towards better personalized approaches to diabetes care. We underline the essential aspects to consider when using RWD and the key features limiting the translational potential of RWD in generating high-quality and applicable RWE. Only if viewed in the context of other study designs and statistical methods, with its pros and cons carefully considered, RWE will exploit its full potential as a complementary or even, in some cases, substitutive source of evidence compared to the expensive evidence obtained from randomized controlled trials.

Identification of subgroups of patients with type 2 diabetes with differences in renal function preservation, comparing patients receiving sodium-glucose co-transporter-2 inhibitors with those receiving dipeptidyl peptidase-4 inhibitors, using a supervised machine-learning algorithm (PROFILE study): A retrospective analysis of a Japanese commercial medical database

AIMS

To investigate the effects of sodium-glucose co-transporter-2 (SGLT2) inhibitors vs. dipeptidyl peptidase-4 (DPP-4) inhibitors on renal function preservation (RFP) using real-world data of patients with type 2 diabetes in Japan, and to identify which subgroups of patients obtained greater RFP benefits with SGLT2 inhibitors vs. DPP-4 inhibitors.

METHODS

We retrospectively analysed claims data recorded in the Medical Data Vision database in Japan of patients with type 2 diabetes (aged ≥18 years) prescribed any SGLT2 inhibitor or any DPP-4 inhibitor between May 2014 and September 2016 (identification period), in whom estimated glomerular filtration rate (eGFR) was measured at least twice (baseline, up to 6 months before the index date; follow-up, 9 to 15 months after the index date) with continuous treatment until the follow-up eGFR. The endpoint was the percentage of patients with RFP, defined as no change or an increase in eGFR from baseline to follow-up. A proprietary supervised learning algorithm (Q-Finder; Quinten, Paris, France) was used to identify the profiles of patients with an additional RFP benefit of SGLT2 inhibitors vs. DPP-4 inhibitors.

RESULTS

Data were available for 990 patients prescribed SGLT2 inhibitors and 4257 prescribed DPP-4 inhibitors. The proportion of patients with RFP was significantly greater in the SGLT2 inhibitor group (odds ratio 1.27; P = 0.01). The Q-Finder algorithm identified four clinically relevant subgroups showing superior RFP with SGLT2 inhibitors (P < 0.1): no hyperlipidaemia and eGFR ≥79 mL/min/1.73 m² ; eGFR ≥79 mL/min/1.73 m² and diabetes duration ≤1.2 years; eGFR ≥75 mL/min/1.73 m² and use of antithrombotic agents; and haemoglobin ≤13.4 g/dL and LDL cholesterol ≥95.1 mg/dL. In each profile, glycaemic control was similar in the two groups.

CONCLUSION

SGLT2 inhibitors were associated with more favourable RFP vs. DPP-4 inhibitors in patients with certain profiles in real-world settings in Japan.