In Low- and Middle- Income Countries (LMICs), machine learning (ML) and artificial intelligence (AI) offer attractive solutions to address the shortage of health care resources and improve the capacity of the local health care infrastructure. However, AI and ML should also be used cautiously, due to potential issues of fairness and algorithmic bias that may arise if not applied properly. Furthermore, populations in LMICs can be particularly vulnerable to bias and fairness in AI algorithms, due to a lack of technical capacity, existing social bias against minority groups, and a lack of legal protections. In order to address the need for better guidance within the context of global health, we describe three basic criteria (Appropriateness, Fairness, and Bias) that can be used to help evaluate the use of machine learning and AI systems: 1) APPROPRIATENESS is the process of deciding how the algorithm should be used in the local context, and properly matching the machine learning model to the target population; 2) BIAS is a systematic tendency in a model to favor one demographic group vs another, which can be mitigated but can lead to unfairness; and 3) FAIRNESS involves examining the impact on various demographic groups and choosing one of several mathematical definitions of group fairness that will adequately satisfy the desired set of legal, cultural, and ethical requirements. Finally, we illustrate how these principles can be applied using a case study of machine learning applied to the diagnosis and screening of pulmonary disease in Pune, India. We hope that these methods and principles can help guide researchers and organizations working in global health who are considering the use of machine learning and artificial intelligence.

One in three adults worldwide has hypertension, which is associated with significant morbidity and mortality. Consequently, there is a global demand for continuous and non-invasive blood pressure (BP) measurements that are convenient, easy to use, and more accurate than the currently available methods for detecting hypertension. This could easily be achieved through the integration of single-site photoplethysmography (PPG) readings into wearable devices, although improved reliability and an understanding of BP estimation accuracy are essential. This review paper focuses on understanding the features of PPG associated with BP and examines the development of this technology over the 2010–2019 period in terms of validation, sample size, diversity of subjects, and datasets used. Challenges and opportunities to move single-site PPG forward are also discussed.

Widespread use of affective sensing in healthcare applications has been limited due to several practical factors, such as lack of comfortable wearable sensors, lack of wireless standards, and lack of low-power affordable hardware. In this paper, we present a new low-cost, low-power wireless sensor platform implemented using the IEEE 802.15.4 wireless standard, and describe the design of compact wearable sensors for long-term measurement of electrodermal activity, temperature, motor activity, and photoplethysmography. We also illustrate the use of this new technology for continuous long-term monitoring of autonomic nervous system and motion data from active infants, children, and adults. We describe several new applications enabled by this system, discuss two specific wearable designs for the wrist and foot, and present sample data.

Hypertension is one of the most prevalent diseases and is often called the “silent killer” because there are usually no early symptoms. Hypertension is also associated with multiple morbidities, including chronic kidney disease and cardiovascular disease. Early detection and intervention are therefore important. The current routine method for diagnosing hypertension is done using a sphygmomanometer, which can only provide intermittent blood pressure readings and can be confounded by various factors, such as white coat hypertension, time of day, exercise, or stress. Consequently, there is an increasing need for a non-invasive, cuff-less, and continuous blood pressure monitoring device. Multi-site photoplethysmography (PPG) is a promising new technology that can measure a range of features of the pulse, including the pulse transit time of the arterial pulse wave, which can be used to continuously estimate arterial blood pressure. This is achieved by detecting the pulse wave at one body site location and measuring the time it takes for it to reach a second, distal location. The purpose of this review is to analyze the current research in multi-site PPG for blood pressure assessment and provide recommendations to guide future research. In a systematic search of the literature from January 2010 to January 2019, we found 13 papers that proposed novel methods using various two-channel PPG systems and signal processing techniques to acquire blood pressure using multi-site PPG that offered promising results. However, we also found a general lack of validation in terms of sample size and diversity of populations.

We present a wearable sensor platform designed for monitoring and studying autonomic nervous system (ANS) activity for the purpose of mental health treatment and interventions. The mobile sensor system consists of a sensor band worn on the ankle that continuously monitors electrodermal activity (EDA), 3-axis acceleration, and temperature. A custom-designed ECG heart monitor worn on the chest is also used as an optional part of the system. The EDA signal from the ankle bands provides a measure sympathetic nervous system activity and used to detect arousal events. The optional ECG data can be used to improve the sensor classification algorithm and provide a measure of emotional “valence.” Both types of sensor bands contain a Bluetooth radio that enables communication with the patient's mobile phone. When a specific arousal event is detected, the phone automatically presents therapeutic and empathetic messages to the patient in the tradition of Cognitive Behavioral Therapy (CBT). As an example of clinical use, we describe how the system is currently being used in an ongoing study for patients with drug-addiction and post-traumatic stress disorder (PTSD).

Wearable sensors enable long-term continuous physiological monitoring, which is important for the treatment and management of many chronic illnesses, neurological disorders, and mental health issues. Examples include: diabetes, autism spectrum disorder (ASD), depression, drug addition, and anxiety disorders. In this paper, we present a few mobile health technologies developed by our group and also discuss emerging opportunities as well as existing challenges. Technologies presented include wearable sensors for electrodermal activity (EDA) and mobile plethysmography as well as mobile phones and the supporting wireless network architecture.