Transforming Diabetes Care Through Artificial Intelligence: The Future Is Here

Second-Generation Digital Health Platforms: Placing the Patient at the Center and Focusing on Clinical Outcomes

Artificial intelligence (AI) digital health systems have drawn much attention over the last decade. However, their implementation into medical practice occurs at a much slower pace than expected. This paper reviews some of the achievements of first-generation AI systems, and the barriers facing their implementation into medical practice. The development of second-generation AI systems is discussed with a focus on overcoming some of these obstacles. Second-generation systems are aimed at focusing on a single subject and on improving patients' clinical outcomes. A personalized closed-loop system designed to improve end-organ function and the patient's response to chronic therapies is presented. The system introduces a platform which implements a personalized therapeutic regimen and introduces quantifiable individualized-variability patterns into its algorithm. The platform is designed to achieve a clinically meaningful endpoint by ensuring that chronic therapies will have sustainable effect while overcoming compensatory mechanisms associated with disease progression and drug resistance. Second-generation systems are expected to assist patients and providers in adopting and implementing of these systems into everyday care.

Use of Machine Learning Approaches in Clinical Epidemiological Research of Diabetes

PURPOSE OF REVIEW

Machine learning approaches-which seek to predict outcomes or classify patient features by recognizing patterns in large datasets-are increasingly applied to clinical epidemiology research on diabetes. Given its novelty and emergence in fields outside of biomedical research, machine learning terminology, techniques, and research findings may be unfamiliar to diabetes researchers. Our aim was to present the use of machine learning approaches in an approachable way, drawing from clinical epidemiological research in diabetes published from 1 Jan 2017 to 1 June 2020.

RECENT FINDINGS

Machine learning approaches using tree-based learners-which produce decision trees to help guide clinical interventions-frequently have higher sensitivity and specificity than traditional regression models for risk prediction. Machine learning approaches using neural networking and "deep learning" can be applied to medical image data, particularly for the identification and staging of diabetic retinopathy and skin ulcers. Among the machine learning approaches reviewed, researchers identified new strategies to develop standard datasets for rigorous comparisons across older and newer approaches, methods to illustrate how a machine learner was treating underlying data, and approaches to improve the transparency of the machine learning process. Machine learning approaches have the potential to improve risk stratification and outcome prediction for clinical epidemiology applications. Achieving this potential would be facilitated by use of universal open-source datasets for fair comparisons. More work remains in the application of strategies to communicate how the machine learners are generating their predictions.

Artificial Intelligence in Health Care: Current Applications and Issues

In recent years, artificial intelligence (AI) technologies have greatly advanced and become a reality in many areas of our daily lives. In the health care field, numerous efforts are being made to implement the AI technology for practical medical treatments. With the rapid developments in machine learning algorithms and improvements in hardware performances, the AI technology is expected to play an important role in effectively analyzing and utilizing extensive amounts of health and medical data. However, the AI technology has various unique characteristics that are different from the existing health care technologies. Subsequently, there are a number of areas that need to be supplemented within the current health care system for the AI to be utilized more effectively and frequently in health care. In addition, the number of medical practitioners and public that accept AI in the health care is still low; moreover, there are various concerns regarding the safety and reliability of AI technology implementations. Therefore, this paper aims to introduce the current research and application status of AI technology in health care and discuss the issues that need to be resolved.

Role of self-care in COVID-19 pandemic for people living with comorbidities of diabetes and hypertension

People living with comorbidities especially chronic non-communicable disease (NCDs) like diabetes and hypertension are at greater risk of acquiring severe form of Corona Virus Disease (COVID-19) infection known to be caused by Severe Acute Respiratory Syndrome-CoV -2 (SARS-CoV-2) due to underlying immunodeficiency. The government has taken various public health measures to reduce the risk of infection, such as physical distancing, Information Education and Communication (IEC) messages regarding hand-washing, usage of masks, and avoidance of unnecessary travel including lockdown to combat the spread of disease. However, nationwide lockdown due to COVID-19 pandemic has also confronted the existing health care system (clinician centric approach) for the management of diabetes and hypertension in India. Using secondary source of data from specific website and search engine a review was done for existing guidelines and literature focusing on the various components of self-care management (patient-centered care) and highlights the importance of self-care management education to cope up with twin pandemic of COVID-19 and NCDs. An attempt was also made to highlight the use of eHealth to manage diabetes and hypertension which may act as a bridge to fill the gap between primary care physician and patient's amid lockdown and help physician to deliver comprehensive care for people suffering from comorbidities.

An Innovative Artificial Intelligence-Based App for the Diagnosis of Gestational Diabetes Mellitus (GDM-AI): Development Study

Background

Gestational diabetes mellitus (GDM) can cause adverse consequences to both mothers and their newborns. However, pregnant women living in low- and middle-income areas or countries often fail to receive early clinical interventions at local medical facilities due to restricted availability of GDM diagnosis. The outstanding performance of artificial intelligence (AI) in disease diagnosis in previous studies demonstrates its promising applications in GDM diagnosis.

Objective

This study aims to investigate the implementation of a well-performing AI algorithm in GDM diagnosis in a setting, which requires fewer medical equipment and staff and to establish an app based on the AI algorithm. This study also explores possible progress if our app is widely used.

Methods

An AI model that included 9 algorithms was trained on 12,304 pregnant outpatients with their consent who received a test for GDM in the obstetrics and gynecology department of the First Affiliated Hospital of Jinan University, a local hospital in South China, between November 2010 and October 2017. GDM was diagnosed according to American Diabetes Association (ADA) 2011 diagnostic criteria. Age and fasting blood glucose were chosen as critical parameters. For validation, we performed k-fold cross-validation (k=5) for the internal dataset and an external validation dataset that included 1655 cases from the Prince of Wales Hospital, the affiliated teaching hospital of the Chinese University of Hong Kong, a non-local hospital. Accuracy, sensitivity, and other criteria were calculated for each algorithm.

Results

The areas under the receiver operating characteristic curve (AUROC) of external validation dataset for support vector machine (SVM), random forest, AdaBoost, k-nearest neighbors (kNN), naive Bayes (NB), decision tree, logistic regression (LR), eXtreme gradient boosting (XGBoost), and gradient boosting decision tree (GBDT) were 0.780, 0.657, 0.736, 0.669, 0.774, 0.614, 0.769, 0.742, and 0.757, respectively. SVM also retained high performance in other criteria. The specificity for SVM retained 100% in the external validation set with an accuracy of 88.7%.

Conclusions

Our prospective and multicenter study is the first clinical study that supports the GDM diagnosis for pregnant women in resource-limited areas, using only fasting blood glucose value, patients’ age, and a smartphone connected to the internet. Our study proved that SVM can achieve accurate diagnosis with less operation cost and higher efficacy. Our study (referred to as GDM-AI study, ie, the study of AI-based diagnosis of GDM) also shows our app has a promising future in improving the quality of maternal health for pregnant women, precision medicine, and long-distance medical care. We recommend future work should expand the dataset scope and replicate the process to validate the performance of the AI algorithms.

Coaching Through Technology: A Systematic Review into Efficacy and Effectiveness for the Ageing Population

Background: Despite the evidence on the positive role of self-management, the adoption of health coaching strategies for older people is still limited. To address these gaps, recent efforts have been made in the ICT sector in order to develop systems for delivering coaching and overcoming barriers relating to scarcity of resources. The aim of this review is to examine the efficacy of personal health coaching systems for older adults using digital virtual agents. Methods: A systematic review of the literature was conducted in December 2019 analyzing manuscripts from four databases over the last 10 years. Nine papers were included. Results: Despite the low number of studies, there was evidence that technology-integrated interventions can deliver benefits for health over usual care. However, the review raises important questions about how to maintain benefits and permanence of behavior change produced by short-term interventions. Conclusion: These systems offer a potential tool to reduce costs, minimize therapist burden and training, and expand the range of clients who can benefit from them. It is desirable that in the future the number of studies will grow, considering other aspects such as the role of the virtual coaches’ characteristics, social-presence, empathy, usability, and health literacy.

Artificial Intelligence: The Future for Diabetes Care

Artificial intelligence (AI) is a fast-growing field and its applications to diabetes, a global pandemic, can reform the approach to diagnosis and management of this chronic condition. Principles of machine learning have been used to build algorithms to support predictive models for the risk of developing diabetes or its consequent complications. Digital therapeutics have proven to be an established intervention for lifestyle therapy in the management of diabetes. Patients are increasingly being empowered for self-management of diabetes, and both patients and health care professionals are benefitting from clinical decision support. AI allows a continuous and burden-free remote monitoring of the patient's symptoms and biomarkers. Further, social media and online communities enhance patient engagement in diabetes care. Technical advances have helped to optimize resource use in diabetes. Together, these intelligent technical reforms have produced better glycemic control with reductions in fasting and postprandial glucose levels, glucose excursions, and glycosylated hemoglobin. AI will introduce a paradigm shift in diabetes care from conventional management strategies to building targeted data-driven precision care.

Deep Physiological Model for Blood Glucose Prediction in T1DM Patients

Accurate estimations for the near future levels of blood glucose are crucial for Type 1 Diabetes Mellitus (T1DM) patients in order to be able to react on time and avoid hypo and hyper-glycemic episodes. Accurate predictions for blood glucose are the base for control algorithms in glucose regulating systems such as the artificial pancreas. Numerous research studies have already been conducted in order to provide predictions for blood glucose levels with particularities in the input signals and underlying models used. These models can be categorized into two major families: those based on tuning glucose physiological-metabolic models and those based on learning glucose evolution patterns based on machine learning techniques. This paper reviews the state of the art in blood glucose predictions for T1DM patients and proposes, implements, validates and compares a new hybrid model that decomposes a deep machine learning model in order to mimic the metabolic behavior of physiological blood glucose methods. The differential equations for carbohydrate and insulin absorption in physiological models are modeled using a Recurrent Neural Network (RNN) implemented using Long Short-Term Memory (LSTM) cells. The results show Root Mean Square Error (RMSE) values under 5 mg/dL for simulated patients and under 10 mg/dL for real patients.

Impact of a "Chart Closure" Hard Stop Alert on Prescribing for Elevated Blood Pressures Among Patients With Diabetes: Quasi-Experimental Study

BACKGROUND

University of California at Los Angeles Health implemented a Best Practice Advisory (BPA) alert for the initiation of an angiotensin-converting enzyme inhibitor (ACEI) or angiotensin-receptor blocker (ARB) for individuals with diabetes. The BPA alert was configured with a "chart closure" hard stop, which demanded a response before closing the chart.

OBJECTIVE

The aim of the study was to evaluate whether the implementation of the BPA was associated with changes in ACEI and ARB prescribing during primary care encounters for patients with diabetes.

METHODS

We defined ACEI and ARB prescribing opportunities as primary care encounters in which the patient had a diabetes diagnosis, elevated blood pressure in recent encounters, no active ACEI or ARB prescription, and no contraindications. We used a multivariate logistic regression model to compare the change in the probability of an ACEI or ARB prescription during opportunity encounters before and after BPA implementation in primary care sites that did (n=30) and did not (n=31) implement the BPA. In an additional subgroup analysis, we compared ACEI and ARB prescribing in BPA implementation sites that had also implemented a pharmacist-led medication management program.

RESULTS

We identified a total of 2438 opportunity encounters across 61 primary care sites. The predicted probability of an ACEI or ARB prescription increased significantly from 11.46% to 22.17% during opportunity encounters in BPA implementation sites after BPA implementation. However, in the subgroup analysis, we only observed a significant improvement in ACEI and ARB prescribing in BPA implementation sites that had also implemented the pharmacist-led program. Overall, the change in the predicted probability of an ACEI or ARB prescription from before to after BPA implementation was significantly greater in BPA implementation sites compared with nonimplementation sites (difference-in-differences of 11.82; P<.001).

CONCLUSIONS

A BPA with a "chart closure" hard stop is a promising tool for the treatment of patients with comorbid diabetes and hypertension with an ACEI or ARB, especially when implemented within the context of team-based care, wherein clinical pharmacists support the work of primary care providers.

Meeting the Challenge of Diabetes in China

China's estimated 114 million people with diabetes pose a massive challenge for China's health policy-makers who have significantly extended health insurance coverage over the past decade. What China is doing now, what it has achieved, and what remains to be done should be of interest to health policy-makers, worldwide. We identify the challenges posed by China's two principal strategies to tackle diabetes: (1) A short-term pilot strategy of health promotion, detection and control of chronic diseases in 265 national demonstration areas (NDAs); and (2) A long-term strategy to extend health promotion and strengthen primary care capacity and health system integration throughout China. Finally, we consider how Chinese innovations in artificial intelligence (AI) and Big Data may contribute to improving diagnosis, controlling complications and increasing access to care. Health system integration in China will require overcoming the fragmentation of a system that still places excessive reliance on local government financing. Moreover, what remains to be done resembles deeper challenges faced by healthcare systems worldwide: the need to upgrade primary care and reduce inequalities in access to health services.

Controlled Heterotypic Pseudo-Islet Assembly of Human β-Cells and Human Umbilical Vein Endothelial Cells Using Magnetic Levitation

β-Cell functionality and survival are highly dependent on the cells' microenvironment and cell–cell interactions. Since the pancreas is a highly vascularized organ, the crosstalk between β-cells and endothelial cells (ECs) is vital to ensure proper function. To understand the interaction of pancreatic β-cells with vascular ECs, we sought to investigate the impact of the spatial distribution on the interaction of human cell line-based β-cells (EndoC-βH3) and human umbilical vein endothelial cells (HUVECs). We focused on the evaluation of three major spatial distributions, which can be found within human islets in vivo, in tissue-engineered heterotypic cell spheroids, so-called pseudo-islets, by controlling the aggregation process using magnetic levitation. We report that heterotypic spheroids formed by spontaneous aggregation cannot be maintained in culture due to HUVEC disassembly over time. In contrast, magnetic levitation allows the formation of stable heterotypic spheroids with defined spatial distribution and significantly facilitated HUVEC integration. To the best of our knowledge, this is the first study that introduces a human-only cell line-based in vitro test system composed of a coculture of β-cells and ECs with a successful stimulation of β-cell secretory function monitored by a glucose-stimulated insulin secretion assays. In addition, we systematically investigate the impact of the spatial distribution on cocultures of human β-cells and ECs, showing that the architecture of pseudo-islets significantly affects β-cell functionality.

Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning

Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.

Artificial Intelligence for the Detection of Diabetic Retinopathy in Primary Care: Protocol for Algorithm Development

Background

Diabetic retinopathy (DR) is one of the most important causes of blindness worldwide, especially in developed countries. In diabetic patients, periodic examination of the back of the eye using a nonmydriatic camera has been widely demonstrated to be an effective system to control and prevent the onset of DR. Convolutional neural networks have been used to detect DR, achieving very high sensitivities and specificities.

Objective

The objective of this is paper was to develop an artificial intelligence (AI) algorithm for the detection of signs of DR in diabetic patients and to scientifically validate the algorithm to be used as a screening tool in primary care.

Methods

Under this project, 2 studies will be conducted in a concomitant way: (1) Development of an algorithm with AI to detect signs of DR in patients with diabetes and (2) A prospective study comparing the diagnostic capacity of the AI algorithm with respect to the actual system of family physicians evaluating the images. The standard reference to compare with will be a blinded double reading conducted by retina specialists. For the development of the AI algorithm, different iterations and workouts will be performed on the same set of data. Before starting each new workout, the strategy of dividing the set date into 2 groups will be used randomly. A group with 80% of the images will be used during the training (training dataset), and the remaining 20% images will be used to validate the results (validation dataset) of each cycle (epoch). During the prospective study, true-positive, true-negative, false-positive, and false-negative values will be calculated again. From here, we will obtain the resulting confusion matrix and other indicators to measure the performance of the algorithm.

Results

Cession of the images began at the end of 2018. The development of the AI algorithm is calculated to last about 3 to 4 months. Inclusion of patients in the cohort will start in early 2019 and is expected to last 3 to 4 months. Preliminary results are expected to be published by the end of 2019.

Conclusions

The study will allow the development of an algorithm based on AI that can demonstrate an equal or superior performance, and that constitutes a complement or an alternative, to the current screening of DR in diabetic patients.

International Registered Report Identifier (IRRID)

PRR1-10.2196/12539