Use of Machine Learning and Hybrid Closed Loop Insulin Delivery at Diabetes Camps

(Hybrid) Closed-Loop Systems: From Announced to Unannounced Exercise

Physical activity and exercise have many beneficial effects on general and type 1 diabetes (T1D) specific health and are recommended for individuals with T1D. Despite these health benefits, many people with T1D still avoid exercise since glycemic management during physical activity poses substantial glycemic and psychological challenges - which hold particularly true for unannounced exercise when using an AID system. Automated insulin delivery (AID) systems have demonstrated their efficacy in improving overall glycemia and in managing announced exercise in numerous studies. They are proven to increase time in range (70-180 mg/dL) and can especially counteract nocturnal hypoglycemia, even when evening exercise was performed. AID-systems consist of a pump administering insulin as well as a CGM sensor (plus transmitter), both communicating with a control algorithm integrated into a device (insulin pump, mobile phone/smart watch). Nevertheless, without manual pre-exercise adaptions, these systems still face a significant challenge around physical activity. Automatically adapting to the rapidly changing insulin requirements during unannounced exercise and physical activity is still the Achilles' heel of current AID systems. There is an urgent need for improving current AID-systems to safely and automatically maintain glucose management without causing derailments - so that going forward, exercise announcements will not be necessary in the future. Therefore, this narrative literature review aimed to discuss technological strategies to how current AID-systems can be improved in the future and become more proficient in overcoming the hurdle of unannounced exercise. For this purpose, the current state-of-the-art therapy recommendations for AID and exercise as well as novel research approaches are presented along with potential future solutions - in order to rectify their deficiencies in the endeavor to achieve fully automated AID-systems even around unannounced exercise.

Machine learning-based algorithm as an innovative approach for the differentiation between diabetes insipidus and primary polydipsia in clinical practice

OBJECTIVE

Differentiation between central diabetes insipidus (cDI) and primary polydipsia (PP) remains challenging in clinical practice. Although the hypertonic saline infusion test led to high diagnostic accuracy, it is a laborious test requiring close monitoring of plasma sodium levels. As such, we leverage machine learning (ML) to facilitate differential diagnosis of cDI.

DESIGN

We analyzed data of 59 patients with cDI and 81 patients with PP from a prospective multicenter study evaluating the hypertonic saline test as new test approach to diagnose cDI. Our primary outcome was the diagnostic accuracy of the ML-based algorithm in differentiating cDI from PP patients.

METHODS

The data set used included 56 clinical, biochemical, and radiological covariates. We identified a set of five covariates which were crucial for differentiating cDI from PP patients utilizing standard ML methods. We developed ML-based algorithms on the data and validated them with an unseen test data set.

RESULTS

Urine osmolality, plasma sodium and glucose, known transsphenoidal surgery, or anterior pituitary deficiencies were selected as input parameters for the basic ML-based algorithm. Testing it on an unseen test data set resulted in a high area under the curve (AUC) score of 0.87. A further improvement of the ML-based algorithm was reached with the addition of MRI characteristics and the results of the hypertonic saline infusion test (AUC: 0.93 and 0.98, respectively).

CONCLUSION

The developed ML-based algorithm facilitated differentiation between cDI and PP patients with high accuracy even if only clinical information and laboratory data were available, thereby possibly avoiding cumbersome clinical tests in the future.

Strengths and Challenges of Closed-Loop Insulin Delivery During Exercise in People With Type 1 Diabetes: Potential Future Directions

Exercise has many physical and psychological benefits and is recommended for people with type 1 diabetes; however, there are many barriers to exercise, including glycemic instability and fear of hypoglycemia. Closed-loop (CL) systems have shown benefit in the overall glycemic management of type 1 diabetes, including improving HbA1c levels and reducing the incidence of nocturnal hypoglycemia; however, these systems are challenged by the rapidly changing insulin needs with exercise. This commentary focuses on the principles, strengths, and challenges of CL in the management of exercise, and discusses potential approaches, including the use of additional physiological signals, to address their shortcomings in the pursuit of fully automated CL systems.