Predicting type 2 diabetes prevalence for people with severe mental illness in a multi-ethnic East London population

Development and validation of a machine learning model for prediction of type 2 diabetes in patients with mental illness

BACKGROUND

Type 2 diabetes (T2D) is approximately twice as common among individuals with mental illness compared with the background population, but may be prevented by early intervention on lifestyle, diet, or pharmacologically. Such prevention relies on identification of those at elevated risk (prediction). The aim of this study was to develop and validate a machine learning model for prediction of T2D among patients with mental illness.

METHODS

The study was based on routine clinical data from electronic health records from the psychiatric services of the Central Denmark Region. A total of 74,880 patients with 1.59 million psychiatric service contacts were included in the analyses. We created 1343 potential predictors from 51 source variables, covering patient-level information on demographics, diagnoses, pharmacological treatment, and laboratory results. T2D was operationalised as HbA1c ≥48 mmol/mol, fasting plasma glucose ≥7.0 mmol/mol, oral glucose tolerance test ≥11.1 mmol/mol or random plasma glucose ≥11.1 mmol/mol. Two machine learning models (XGBoost and regularised logistic regression) were trained to predict T2D based on 85% of the included contacts. The predictive performance of the best performing model was tested on the remaining 15% of the contacts.

RESULTS

The XGBoost model detected patients at high risk 2.7 years before T2D, achieving an area under the receiver operating characteristic curve of 0.84. Of the 996 patients developing T2D in the test set, the model issued at least one positive prediction for 305 (31%).

CONCLUSION

A machine learning model can accurately predict development of T2D among patients with mental illness based on routine clinical data from electronic health records. A decision support system based on such a model may inform measures to prevent development of T2D in this high-risk population.

Balancing accuracy and Interpretability: An R package assessing complex relationships beyond the Cox model and applications to clinical prediction

BACKGROUND

Accurate and interpretable models are essential for clinical decision-making, where predictions can directly impact patient care. Machine learning (ML) survival methods can handle complex multidimensional data and achieve high accuracy but require post-hoc explanations. Traditional models such as the Cox Proportional Hazards Model (Cox-PH) are less flexible, but fast, stable, and intrinsically transparent. Moreover, ML does not always outperform Cox-PH in clinical settings, warranting a diligent model validation. We aimed to develop a set of R functions to help explore the limits of Cox-PH compared to the tree-based and deep learning survival models for clinical prediction modelling, employing ensemble learning and nested cross-validation.

METHODS

We developed a set of R functions, publicly available as the package "survcompare". It supports Cox-PH and Cox-Lasso, and Survival Random Forest (SRF) and DeepHit are the ML alternatives, along with the ensemble methods integrating Cox-PH with SRF or DeepHit designed to isolate the marginal value of ML. The package performs a repeated nested cross-validation and tests for statistical significance of the ML's superiority using the survival-specific performance metrics, the concordance index, time-dependent AUC-ROC and calibration slope. To get practical insights, we applied this methodology to clinical and simulated datasets with varying complexities and sizes.

RESULTS

In simulated data with non-linearities or interactions, ML models outperformed Cox-PH at sample sizes ≥ 500. ML superiority was also observed in imaging and high-dimensional clinical data. However, for tabular clinical data, the performance gains of ML were minimal; in some cases, regularised Cox-Lasso recovered much of the ML's performance advantage with significantly faster computations. Ensemble methods combining Cox-PH and ML predictions were instrumental in quantifying Cox-PH's limits and improving ML calibration. Traditional models like Cox-PH or Cox-Lasso should not be overlooked while developing clinical predictive models from tabular data or data of limited size.

CONCLUSION

Our package offers researchers a framework and practical tool for evaluating the accuracy-interpretability trade-off, helping make informed decisions about model selection.

A machine learning tool for identifying patients with newly diagnosed diabetes in primary care

BACKGROUND AND AIM

It is crucial to identify a diabetes diagnosis early. Create a predictive model utilizing machine learning (ML) to identify new cases of diabetes in primary health care (PHC).

METHODS

A case-control study utilizing data on PHC visits for sex-, age, and PHC-matched controls. Stochastic gradient boosting was used to construct a model for predicting cases of diabetes based on diagnostic codes from PHC consultations during the year before index (diagnosis) date and number of consultations. Variable importance was estimated using the normalized relative influence (NRI) score. Risks of having diabetes were calculated using odds ratios of marginal effects (ORME). Four groups by age and sex were studied, age-groups 35-64 years and ≥ 65 years in men and women, respectively.

RESULTS

The most important predictive factors were hypertension with NRI 21.4-29.7 %, and obesity 4.8-15.2 %. The NRI for other top ten diagnoses and administrative codes generally ranged 1.0-4.2 %.

CONCLUSIONS

Our data confirm the known risk patterns for predicting a new diagnosis of diabetes, and the need to test blood glucose frequently. To assess the full potential of ML for risk prediction purposes in clinical practice, future studies could include clinical data on life-style patterns, laboratory tests and prescribed medication.

Schizophrenia and type 2 diabetes risk: a systematic review and meta-analysis

Objectives

The metabolic syndrome in patients with schizophrenia has consistently been a challenge for clinicians. Previous studies indicate that individuals with schizophrenia are highly prone to developing type 2 diabetes mellitus (T2DM). In recent years, a continuous stream of new observational studies has been reported, emphasizing the pressing need for clinicians to gain a more precise understanding of the association between schizophrenia and T2DM. The objective of this meta-analysis is to integrate new observational studies and further explore the potential link between schizophrenia and the risk of T2DM.

Methods

We conducted a comprehensive search of PubMed, Cochrane Library, Embase, and Web of Science using medical subject headings (MeSH) and relevant keywords. The risk of bias in cohort studies and case-control studies was assessed using the Newcastle-Ottawa Scale (NOS), while cross-sectional studies were evaluated using the Agency for Healthcare Research and Quality scale (AHRQ), scoring was based on the content of the original studies. A fixed-effects model was employed if P > 0.1 and I2 ≤ 50%, indicating low heterogeneity. Conversely, a random-effects model was utilized if I2 > 50%, indicating substantial heterogeneity. Publication bias was assessed using funnel plots and Egger's test. Statistical analyses were carried out using Stata statistical software version 14.0.

Results

This meta-analysis comprised 32 observational studies, involving a total of 2,007,168 patients with schizophrenia and 35,883,980 without schizophrenia, published from 2004 to 2023. The pooled analysis revealed a significant association between a history of schizophrenia and an increased risk of T2DM (Odds Ratio [OR] = 2.15; 95% Confidence Interval [CI]: 1.83-2.52; I2 = 98.9%, P < 0.001). Stratified by gender, females with schizophrenia (OR = 2.12; 95% CI: 1.70-2.64; I2 = 90.7%, P < 0.001) had a significantly higher risk of T2DM than males (OR = 1.68; 95% CI: 1.39-2.04; I2 = 91.3%, P < 0.001). Regarding WHO regions, EURO (OR = 2.73; 95% CI: 2.23-3.35; I2 = 97.5%, P < 0.001) exhibited a significantly higher risk of T2DM compared to WPRO (OR = 1.72; 95% CI: 1.32-2.23; I2 = 95.2%, P < 0.001) and AMRO (OR = 1.82; 95% CI: 1.40-2.37; I2 = 99.1%, P < 0.001). In terms of follow-up years, the >20 years subgroup (OR = 3.17; 95% CI: 1.24-8.11; I2 = 99.4%, P < 0.001) showed a significantly higher risk of T2DM than the 10-20 years group (OR = 2.26; 95% CI: 1.76-2.90; I2 = 98.6%, P < 0.001) and <10 years group (OR = 1.68; 95% CI: 1.30-2.19; I2 = 95.4%, P < 0.001).

Conclusions

This meta-analysis indicates a strong association between schizophrenia and an elevated risk of developing diabetes, suggesting that schizophrenia may function as an independent risk factor for T2DM.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42023465826.