Predicting Progression Patterns of Type 2 Diabetes using Multi-sensor Measurements

A systematic review on artificial intelligence approaches for smart health devices

In the context of smart health, the use of wearable Internet of Things (IoT) devices is becoming increasingly popular to monitor and manage patients' health conditions in a more efficient and personalized way. However, choosing the most suitable artificial intelligence (AI) methodology to analyze the data collected by these devices is crucial to ensure the reliability and effectiveness of smart healthcare applications. Additionally, protecting the privacy and security of health data is an area of growing concern, given the sensitivity and personal nature of such information. In this context, machine learning (ML) and deep learning (DL) are emerging as successful technologies because they are suitable for application to advanced analysis and prediction of healthcare scenarios. Therefore, the objective of this work is to contribute to the current state of the literature by identifying challenges, best practices, and future opportunities in the field of smart health. We aim to provide a comprehensive overview of the AI methodologies used, the neural network architectures adopted, and the algorithms employed, as well as examine the privacy and security issues related to the management of health data collected by wearable IoT devices. Through this systematic review, we aim to offer practical guidelines for the design, development, and implementation of AI solutions in smart health, to improve the quality of care provided and promote patient well-being. To pursue our goal, several articles focusing on ML or DL network architectures were selected and reviewed. The final discussion highlights research gaps yet to be investigated, as well as the drawbacks and vulnerabilities of existing IoT applications in smart healthcare.

Artificial Intelligence-Based Digital Biomarkers for Type 2 Diabetes: A Review

Type 2 diabetes mellitus (T2DM), a complex metabolic disorder that burdens the health care system, requires early detection and treatment. Recent strides in digital health technologies, coupled with artificial intelligence (AI), may have the potential to revolutionize T2DM screening, diagnosis of complications, and management through the development of digital biomarkers. This review provides an overview of the potential applications of AI-driven biomarkers in the context of screening, diagnosing complications, and managing patients with T2DM. The benefits of using multisensor devices to develop digital biomarkers are discussed. The summary of these findings and patterns between model architecture and sensor type are presented. In addition, we highlight the pivotal role of AI techniques in clinical intervention and implementation, encompassing clinical decision support systems, telemedicine interventions, and population health initiatives. Challenges such as data privacy, algorithm interpretability, and regulatory considerations are also highlighted, alongside future research directions to explore the use of AI-driven digital biomarkers in T2DM screening and management.

Need for an Artificial Intelligence-based Diabetes Care Management System in India and the United States

Objective

Diabetes mellitus is an important chronic disease that is prevalent around the world. Different countries and diverse cultures use varying approaches to dealing with this chronic condition. Also, with the advancement of computation and automated decision-making, many tools and technologies are now available to patients suffering from this disease. In this work, the investigators attempt to analyze approaches taken towards managing this illness in India and the United States.

Methods

In this work, the investigators have used available literature and data to compare the use of artificial intelligence in diabetes management.

Findings

The article provides key insights to comparison of diabetes management in terms of the nature of the healthcare system, availability, electronic health records, cultural factors, data privacy, affordability, and other important variables. Interestingly, variables such as quality of electronic health records, and cultural factors are key impediments in implementing an efficiency-driven management system for dealing with this chronic disease.

Conclusion

The article adds to the body of knowledge associated with the management of this disease, establishing a critical need for using artificial intelligence in diabetes care management.

An early warning model of type 2 diabetes risk based on POI visit history and food access management

Type 2 diabetes (T2D) is a long-term, highly prevalent disease that provides extensive data support in spatial-temporal user case data mining studies. In this paper, we present a novel T2D food access early risk warning model that aims to emphasize health management awareness among susceptible populations. This model incorporates the representation of T2D-related food categories with graph convolutional networks (GCN), enabling the diet risk visualization from the geotagged Twitter visit records on a map. A long short-term memory (LSTM) module is used to enhance the performance of the case temporal feature extraction and location approximate predictive approach. Through an analysis of the resulting data set, we highlight the food effect category has on T2D early risk visualization and user food access management on the map. Moreover, our proposed method can provide suggestions to T2D susceptible patients on diet management.

Obesity Prediction with EHR Data: A deep learning approach with interpretable elements

Childhood obesity is a major public health challenge. Early prediction and identification of the children at an elevated risk of developing childhood obesity may help in engaging earlier and more effective interventions to prevent and manage obesity. Most existing predictive tools for childhood obesity primarily rely on traditional regression-type methods using only a few hand-picked features and without exploiting longitudinal patterns of children's data. Deep learning methods allow the use of high-dimensional longitudinal datasets. In this paper, we present a deep learning model designed for predicting future obesity patterns from generally available items on children's medical history. To do this, we use a large unaugmented electronic health records dataset from a large pediatric health system in the US. We adopt a general LSTM network architecture and train our proposed model using both static and dynamic EHR data. To add interpretability, we have additionally included an attention layer to calculate the attention scores for the timestamps and rank features of each timestamp. Our model is used to predict obesity for ages between 3-20 years using the data from 1-3 years in advance. We compare the performance of our LSTM model with a series of existing studies in the literature and show it outperforms their performance in most age ranges.

Flexible-Window Predictions on Electronic Health Records

Various types of machine learning techniques are available for analyzing electronic health records (EHRs). For predictive tasks, most existing methods either explicitly or implicitly divide these time-series datasets into predetermined observation and prediction windows. Patients have different lengths of medical history and the desired predictions (for purposes such as diagnosis or treatment) are required at different times in the future. In this paper, we propose a method that uses a sequence-to-sequence generator model to transfer an input sequence of EHR data to a sequence of user-defined target labels, providing the end-users with "flexible" observation and prediction windows to define. We use adversarial and semi-supervised approaches in our design, where the sequence-to-sequence model acts as a generator and a discriminator distinguishes between the actual (observed) and generated labels. We evaluate our models through an extensive series of experiments using two large EHR datasets from adult and pediatric populations. In an obesity predicting case study, we show that our model can achieve superior results in flexible-window prediction tasks, after being trained once and even with large missing rates on the input EHR data. Moreover, using a number of attention analysis experiments, we show that the proposed model can effectively learn more relevant features in different prediction tasks.

Transformer-based Multi-target Regression on Electronic Health Records for Primordial Prevention of Cardiovascular Disease

Machine learning algorithms have been widely used to capture the static and temporal patterns within electronic health records (EHRs). While many studies focus on the (primary) prevention of diseases, primordial prevention (preventing the factors that are known to increase the risk of a disease occurring) is still widely under-investigated. In this study, we propose a multi-target regression model leveraging transformers to learn the bidirectional representations of EHR data and predict the future values of 11 major modifiable risk factors of cardiovascular disease (CVD). Inspired by the proven results of pre-training in natural language processing studies, we apply the same principles on EHR data, dividing the training of our model into two phases: pre-training and fine-tuning. We use the fine-tuned transformer model in a "multi-target regression" theme. Following this theme, we combine the 11 disjoint prediction tasks by adding shared and target-specific layers to the model and jointly train the entire model. We evaluate the performance of our proposed method on a large publicly available EHR dataset. Through various experiments, we demonstrate that the proposed method obtains a significant improvement (12.6% MAE on average across all 11 different outputs) over the baselines.