Identifying patients at increased risk of hypoglycaemia in primary care: Development of a machine learning-based screening tool

Screening for Hypoglycaemia Risk and Medication Changes in Diabetes Patients Using Pharmacy Dispensing Data

Background: To improve hypoglycaemia management in primary care, more insight is needed into the opportunities to screen for hypoglycaemia risk and subsequent treatment modification using routinely available data. Our primary aim was to assess the number of diabetes patients with an estimated high risk of hypoglycaemia and describe the treatment changes in these patients using pharmacy dispensing data. Additionally, our aim was to investigate patient characteristics associated with such treatment changes. Methods: A drug utilisation cohort study with a 1-year follow-up using the IADB.nl pharmacy database was conducted. Patients aged 35 years or older who received at least two glucose-lowering medication dispensings in 2019 were included. Hypoglycaemia risk was determined using a validated algorithm based on patient demographics and dispensing data. The hypoglycaemia risk score ranged between 0 and 1. The anniversary method was used to evaluate treatment changes after 1 year. Factors associated with treatment changes were assessed by multinomial logistic regression. Results: Around one-quarter (26.9%) of the 36,628 included patients had a hypoglycaemia score of 0.6 or more. After a 1-year follow-up, the majority of these patients (88.9%) experienced no diabetes treatment changes. De-intensification was observed for 8.8% and intensification for 2.3%. Having a high-risk score, being female, and being younger in age were associated with de-intensification. Conclusions: A substantial number of primary care patients using glucose-lowering medications appear at risk of hypoglycaemia, whereas few of them undergo medication de-intensification. Pharmacy dispensing data can be helpful in screening for diabetes patients in whom a review of treatment is indicated.

Process evaluation of a pharmacist-led intervention aimed at deprescribing and appropriate use of cardiometabolic medication among adult people with type 2 diabetes

BACKGROUND

A quasi-experimental study investigated a pharmacist-led intervention aimed at deprescribing and medication management among adult patients with type 2 diabetes at risk of hypoglycaemia.

OBJECTIVE

This study aimed to evaluate the process of implementing the intervention consisting of a tailored clinical medication review (CMR) supported by a training and a toolbox.

METHODS

Mixed-methods study based on the Grant framework, including the domains "recruitment," "delivery of intervention" and "response" of pharmacists and patients. Data collected were administrative logs, semi-structured observations of patient consultations (n = 8), interviews with pharmacists (n = 16) and patient-reported experience measure (PREM) questionnaires (n = 66).

RESULTS

Tailored CMRs were conducted largely as intended for 90 patients from 14 pharmacies. Although patient selection based on a medication-derived hypoglycaemia risk score was considered useful, pharmacists experienced barriers to proposing deprescribing in patients with recent medication changes, without current hypoglycaemic events, or treated by medical specialists. The training and toolbox were evaluated positively by the pharmacists. Overall, patients were satisfied with the CMR.

CONCLUSION

Pharmacists and patients valued the CMR focusing on deprescribing and medication management. To optimize implementation and effectiveness of the intervention, improvements can be made to the patient selection, pharmacist training and the collaboration between healthcare professionals.

A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review

Diabetes as a metabolic illness can be characterized by increased amounts of blood glucose. This abnormal increase can lead to critical detriment to the other organs such as the kidneys, eyes, heart, nerves, and blood vessels. Therefore, its prediction, prognosis, and management are essential to prevent harmful effects and also recommend more useful treatments. For these goals, machine learning algorithms have found considerable attention and have been developed successfully. This review surveys the recently proposed machine learning (ML) and deep learning (DL) models for the objectives mentioned earlier. The reported results disclose that the ML and DL algorithms are promising approaches for controlling blood glucose and diabetes. However, they should be improved and employed in large datasets to affirm their applicability.

Potential applications and performance of machine learning techniques and algorithms in clinical practice: A systematic review

PURPOSE

The advent of clinically adapted machine learning algorithms can solve numerous problems ranging from disease diagnosis and prognosis to therapy recommendations. This systematic review examines the performance of machine learning (ML) algorithms and evaluates the progress made to date towards their implementation in clinical practice.

METHODS

Systematic searching of databases (PubMed, MEDLINE, Scopus, Google Scholar, Cochrane Library and WHO Covid-19 database) to identify original articles published between January 2011 and October 2021. Studies reporting ML techniques in clinical practice involving humans and ML algorithms with a performance metric were considered.

RESULTS

Of 873 unique articles identified, 36 studies were eligible for inclusion. The XGBoost (extreme gradient boosting) algorithm showed the highest potential for clinical applications (n = 7 studies); this was followed jointly by random forest algorithm, logistic regression, and the support vector machine, respectively (n = 5 studies). Prediction of outcomes (n = 33), in particular Inflammatory diseases (n = 7) received the most attention followed by cancer and neuropsychiatric disorders (n = 5 for each) and Covid-19 (n = 4). Thirty-three out of the thirty-six included studies passed more than 50% of the selected quality assessment criteria in the TRIPOD checklist. In contrast, none of the studies could achieve an ideal overall bias rating of 'low' based on the PROBAST checklist. In contrast, only three studies showed evidence of the deployment of ML algorithm(s) in clinical practice.

CONCLUSIONS

ML is potentially a reliable tool for clinical decision support. Although advocated widely in clinical practice, work is still in progress to validate clinically adapted ML algorithms. Improving quality standards, transparency, and interpretability of ML models will further lower the barriers to acceptability.

Identifying patients at increased risk of hypoglycaemia in primary care: Development of a machine learning-based screening tool

INTRODUCTION

In primary care, identifying patients with type 2 diabetes (T2D) who are at increased risk of hypoglycaemia is important for the prevention of hypoglycaemic events. We aimed to develop a screening tool based on machine learning to identify such patients using routinely available demographic and medication data.

METHODS

We used a cohort study design and the Groningen Initiative to ANalyse Type 2 diabetes Treatment (GIANTT) medical record database to develop models for hypoglycaemia risk. The first hypoglycaemic event in the observation period (2007-2013) was the outcome. Demographic and medication data were used as predictor variables to train machine learning models. The performance of the models was compared with a model using additional clinical data using fivefold cross validation with the area under the receiver operator characteristic curve (AUC) as a metric.

RESULTS

We included 13,876 T2D patients. The best performing model including only demographic and medication data was logistic regression with least absolute shrinkage and selection operator, with an AUC of 0.71. Ten variables were included (odds ratio): male gender (0.997), age (0.990), total drug count (1.012), glucose-lowering drug count (1.039), sulfonylurea use (1.62), insulin use (1.769), pre-mixed insulin use (1.109), insulin count (1.827), insulin duration (1.193), and antidepressant use (1.05). The proposed model obtained a similar performance to the model using additional clinical data.

CONCLUSION

Using demographic and medication data, a model for identifying patients at increased risk of hypoglycaemia was developed using machine learning. This model can be used as a tool in primary care to screen for patients with T2D who may need additional attention to prevent or reduce hypoglycaemic events.