Feasibility of wearable monitors to detect heart rate variability in children with hand, foot and mouth disease.

Hand foot and mouth disease (HFMD) is caused by a variety of enteroviruses, and occurs in large outbreaks in which a small proportion of children deteriorate rapidly with cardiopulmonary failure. Determining which children are likely to deteriorate is difficult and health systems may become overloaded during outbreaks as many children require hospitalization for monitoring. Heart rate variability (HRV) may help distinguish those with more severe diseases but requires simple scalable methods to collect ECG data.We carried out a prospective observational study to examine the feasibility of using wearable devices to measure HRV in 142 children admitted with HFMD at a children's hospital in Vietnam. ECG data were collected in all children. HRV indices calculated were lower in those with enterovirus A71 associated HFMD compared to those with other viral pathogens.HRV analysis collected from wearable devices is feasible in a low and middle income country (LMIC) and may help classify disease severity in HFMD.

Quantifying the impact of COVID-19 on essential health services: a comparison of interrupted time series analysis using Prophet and Poisson regression models.

BACKGROUND: Coronavirus disease 2019 (COVID-19) altered healthcare utilization patterns. However, there is a dearth of literature comparing methods for quantifying the extent to which the pandemic disrupted healthcare service provision in sub-Saharan African countries. OBJECTIVE: To compare interrupted time series analysis using Prophet and Poisson regression models in evaluating the impact of COVID-19 on essential health services. METHODS: We used reported data from Uganda's Health Management Information System from February 2018 to December 2020. We compared Prophet and Poisson models in evaluating the impact of COVID-19 on new clinic visits, diabetes clinic visits, and in-hospital deliveries between March 2020 to December 2020 and across the Central, Eastern, Northern, and Western regions of Uganda. RESULTS: The models generated similar estimates of the impact of COVID-19 in 10 of the 12 outcome-region pairs evaluated. Both models estimated declines in new clinic visits in the Central, Northern, and Western regions, and an increase in the Eastern Region. Both models estimated declines in diabetes clinic visits in the Central and Western regions, with no significant changes in the Eastern and Northern regions. For in-hospital deliveries, the models estimated a decline in the Western Region, no changes in the Central Region, and had different estimates in the Eastern and Northern regions. CONCLUSIONS: The Prophet and Poisson models are useful in quantifying the impact of interruptions on essential health services during pandemics but may result in different measures of effect. Rigor and multimethod triangulation are necessary to study the true effect of pandemics on essential health services.

Rethinking global digital health and AI-for-health innovation challenges.

Digital health technologies can help tackle challenges in global public health. Digital and AI-for-Health Challenges, controlled events whose goal is to generate solutions to a given problem in a defined period of time, are one way of catalysing innovation. This article proposes an expanded investment framework for Global Health AI and digitalhealth Innovation that goes beyond traditional factors such as return on investment. Instead, we propose non monetary and non GDP metrics, such as Disability Adjusted Life Years or achievement of universal health coverage. Furthermore, we suggest a venture building approach around global health, which includes filtering of participants to reduce opportunity cost, close integration of implementation scientists and an incubator for the long-term development of ideas resulting from the challenge. Finally, we emphasize the need to strengthen human capital across a range of areas in local innovation, implementation-science, and in health services.

Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning.

Images depicting dark skin tones are significantly underrepresented in the educational materials used to teach primary care physicians and dermatologists to recognize skin diseases. This could contribute to disparities in skin disease diagnosis across different racial groups. Previously, domain experts have manually assessed textbooks to estimate the diversity in skin images. Manual assessment does not scale to many educational materials and introduces human errors. To automate this process, we present the Skin Tone Analysis for Representation in EDucational materials (STAR-ED) framework, which assesses skin tone representation in medical education materials using machine learning. Given a document (e.g., a textbook in .pdf), STAR-ED applies content parsing to extract text, images, and table entities in a structured format. Next, it identifies images containing skin, segments the skin-containing portions of those images, and estimates the skin tone using machine learning. STAR-ED was developed using the Fitzpatrick17k dataset. We then externally tested STAR-ED on four commonly used medical textbooks. Results show strong performance in detecting skin images (0.96 ± 0.02 AUROC and 0.90 ± 0.06 F1 score) and classifying skin tones (0.87 ± 0.01 AUROC and 0.91 ± 0.00 F1 score). STAR-ED quantifies the imbalanced representation of skin tones in four medical textbooks: brown and black skin tones (Fitzpatrick V-VI) images constitute only 10.5% of all skin images. We envision this technology as a tool for medical educators, publishers, and practitioners to assess skin tone diversity in their educational materials.

Multimorbidity in African ancestry populations: a scoping review.

OBJECTIVES: Multimorbidity (MM) is a growing concern linked to poor outcomes and higher healthcare costs. While most MM research targets European ancestry populations, the prevalence and patterns in African ancestry groups remain underexplored. This study aimed to identify and summarise the available literature on MM in populations with African ancestry, on the continent, and in the diaspora. DESIGN: A scoping review was conducted in five databases (PubMed, Web of Science, Scopus, Science Direct and JSTOR) in July 2022. Studies were selected based on predefined criteria, with data extraction focusing on methodology and findings. Descriptive statistics summarised the data, and a narrative synthesis highlighted key themes. RESULTS: Of the 232 publications on MM in African-ancestry groups from 2010 to June 2022-113 examined continental African populations, 100 the diaspora and 19 both. Findings revealed diverse MM patterns within and beyond continental Africa. Cardiovascular and metabolic diseases are predominant in both groups (80% continental and 70% diaspora). Infectious diseases featured more in continental studies (58% continental and 16% diaspora). Although many papers did not specifically address these features, as in previous studies, older age, being women and having a lower socioeconomic status were associated with a higher prevalence of MM, with important exceptions. Research gaps identified included limited data on African-ancestry individuals, inadequate representation, under-represented disease groups, non-standardised methodologies, the need for innovative data strategies, and insufficient translational research. CONCLUSION: The growing global MM prevalence is mirrored in African-ancestry populations. Recognising the unique contexts of African-ancestry populations is essential when addressing the burden of MM. This review emphasises the need for additional research to guide and enhance healthcare approaches for African-ancestry populations, regardless of their geographic location.

Hierarchical Representation of Complex Intervention Sequences for Automated Subgroup Analysis in Critical Care Settings.

Our understanding of the impact of interventions in critical care is limited by the lack of techniques that represent and analyze complex intervention spaces applied across heterogeneous patient populations. Existing work has mainly focused on selecting a few interventions and representing them as binary variables, resulting in oversimplification of intervention representation. The goal of this study is to find effective representations of sequential interventions to support intervention effect analysis. To this end, we have developed Hi-RISE (Hierarchical Representation of Intervention Sequences), an approach that transforms and clusters sequential interventions into a latent space, with the resulting clusters used for heterogeneous treatment effect analysis. We apply this approach to the MIMIC III dataset and identified intervention clusters and corresponding subpopulations with peculiar odds of 28-day mortality. Our approach may lead to a better understanding of the subgroup-level effects of sequential interventions and improve targeted intervention planning in critical care settings.

Principled Subpopulation Analysis of the BetterBirth Study and the Impact of WHO's Safe Childbirth Checklist Intervention.

The World Health Organization (WHO) developed the Safe Childbirth Checklist as an intervention to improve care and outcomes in maternal and newborn health. The original study reported that the intervention did not significantly improve the outcomes. In this work, we employ a principled data-driven analysis to identify subpopulations with divergent characteristics: 1) vulnerable subgroups with the highest risk of neonatal deaths and 2) subgroups in the intervention arm that benefited from the Checklist intervention with significantly reduced risks of deaths and complications. Results demonstrate that low birth weight represented the most vulnerable group, whereas mother-baby dyads described by normal gestational age at birth, known parity, and unknown number of abortions was found to benefit from the Checklist intervention (OR : 0.70, 95%CI : 0.62-0.79, p < 0.001). Generally, the flexibility of our approach helps to answer subgroup-based queries in the broader global health domain, which also provides further insights to domain experts.

Detection of Anomalous Patterns Associated with the Impact of Medications on 30-Day Hospital Readmission Rates in Diabetes Care.

Improving quality of care in diabetes requires a good understanding of variations in diabetes outcomes and related interventions. However, little is known about the impact of diabetes interventions on outcome measures at the subpopulation-level. In this study, we developed methods that combine causal inference techniques with subset scanning techniques to study the heterogeneous effects of treatments on binary health outcomes. We analyzed a diabetes dataset consisting of 70,000 initial inpatient encounters to investigate the anomalous patterns associated with the impact of 4 anti-diabetic medication classes on 30-day readmission in diabetes. We discovered anomalous subpopulations where the likelihood of readmission was up to 1.8 times higher than that of the overall population suggesting subpopulation-level heterogeneity. Identifying such subpopulations may lead to a better understanding of the heterogeneous effects of treatments and improve targeted intervention planning.

DeepMI: Deep multi-lead ECG fusion for identifying myocardial infarction and its occurrence-time.

Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detection of MI and information regarding its occurrence-time in particular, would enable timely interventions that may improve patient outcomes, thereby reducing the global rise in CVD deaths. Electrocardiogram (ECG) recordings are currently used to screen MI patients. However, manual inspection of ECGs is time-consuming and prone to subjective bias. Machine learning methods have been adopted for automated ECG diagnosis, but most approaches require extraction of ECG beats or consider leads independently of one another. We propose an end-to-end deep learning approach, DeepMI, to classify MI from Normal cases as well as identifying the time-occurrence of MI (defined as Acute, Recent and Old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level. In order to minimise computational overhead, we employ transfer learning using existing computer vision networks. Moreover, we use recurrent neural networks to encode the longitudinal information inherent in ECGs. We validated DeepMI on a dataset collected from 17,381 patients, in which over 323,000 samples were extracted per ECG lead. We were able to classify Normal cases as well as Acute, Recent and Old onset cases of MI, with AUROCs of 96.7%, 82.9%, 68.6% and 73.8%, respectively. We have demonstrated a multi-lead fusion approach to detect the presence and occurrence-time of MI. Our end-to-end framework provides flexibility for different levels of multi-lead ECG fusion and performs feature extraction via transfer learning.

Data-level Linkage of Multiple Surveys for Improved Understanding of Global Health Challenges.

Data-driven approaches can provide more enhanced insights for domain experts in addressing critical global health challenges, such as newborn and child health, using surveys (e.g., Demographic Health Survey). Though there are multiple surveys on the topic, data-driven insight extraction and analysis are often applied on these surveys separately, with limited efforts to exploit them jointly, and hence results in poor prediction performance of critical events, such as neonatal death. Existing machine learning approaches to utilise multiple data sources are not directly applicable to surveys that are disjoint on collection time and locations. In this paper, we propose, to the best of our knowledge, the first detailed work that automatically links multiple surveys for the improved predictive performance of newborn and child mortality and achieves cross-study impact analysis of covariates.

Data-Driven Sequential Uptake Pattern Discovery for Family Planning Studies.

Family planning is a crucial component of sustainable global development and is essential for achieving universal health coverage. Specifically, contraceptive use improves the health of women and children in several ways, including reducing maternal mortality risks, increasing child survival rates through birth spacing, and improving the nutritional status of both mother and children. This paper presents a data-driven approach to study the dynamics of contraceptive use and discontinuation in Sub-Saharan African (SSA) countries. We aim to provide policymakers with discriminating contraceptive use patterns under different discontinuation reasons, contraceptive uptake distributions, and transition information across contraceptive types. We used Demographic Health Survey (DHS) Calendar data from five SSA countries. One recurrent pattern found was that continuous usage of injectables resulted in discontinuation due to health concerns in four out of five countries studied. This type of temporal analysis can aid intervention development to support sustainable development goals in Family Planning.

Coronary Artery Disease: Optimal Lipoprotein(a) for Survival-Lower Is Better? A Large Cohort With 43,647 Patients.

Background: A high level of lipoprotein(a) can lead to a high risk of cardiovascular events or mortality. However, the association of moderately elevated lipoprotein(a) levels (≥15 mg/dL) with long-term prognosis among patients with coronary artery disease (CAD) is still uncertain. Hence, we aim to systematically analyzed the relevance of baseline plasma lipoprotein(a) levels to long-term mortality in a large cohort of CAD patients. Methods: We obtained data from 43,647 patients who were diagnosed with CAD and had follow-up information from January 2007 to December 2018. The patients were divided into two groups (<15 and ≥15 mg/dL). The primary endpoint was long-term all-cause death. Kaplan-Meier curve analysis and Cox proportional hazards models were used to investigate the association between moderately elevated baseline lipoprotein(a) levels (≥15 mg/dL) and long-term all-cause mortality. Results: During a median follow-up of 5.04 years, 3,941 (18.1%) patients died. We observed a linear association between lipoprotein(a) levels and long-term all-cause mortality. Compared with lipoprotein(a) concentrations <15 mg/dL, lipoprotein(a) ≥15 mg/dL was associated with a significantly higher risk of all-cause mortality [adjusted hazard ratio (aHR) 1.10, 95%CI: 1.04-1.16, P-values = 0.001). Similar results were found for the subgroup analysis of non-acute myocardial infarction, non-percutaneous coronary intervention, chronic heart failure, diabetes mellitus, or non-chronic kidney diseases. Conclusion: Moderately elevated baseline plasma lipoprotein(a) levels (≥15 mg/dL) are significantly associated with higher all-cause mortality in patients with CAD. Our finding provides a rationale for testing the lipoprotein(a)-reducing hypothesis with lower targets (even <15 mg/dL) in CAD outcome trials.

A Spectral-longitudinal Model for Detection of Heart Attack from 12-lead Electrocardiogram Waveforms.

Cardiovascular diseases (CVDs) remain responsible for millions of deaths annually. Myocardial infarction (MI) is the most prevalent condition among CVDs. Although datadriven approaches have been applied to predict CVDs from ECG signals, comparatively little work has been done on the use of multiple-lead ECG traces and their efficient integration to diagnose CVDs. In this paper, we propose an end-to-end trainable and joint spectral-longitudinal model to predict heart attack using data-level fusion of multiple ECG leads. The spectral stage transforms the time-series waveforms to stacked spectrograms and encodes the frequency-time characteristics, whilst the longitudinal model helps to utilise the temporal dependency that exists in these waveforms using recurrent networks. We validate the proposed approach using a public MI dataset. Our results show that the proposed spectrallongitudinal model achieves the highest performance compared to the baseline methods.

PlethAugment: GAN-Based PPG Augmentation for Medical Diagnosis in Low-Resource Settings.

The paucity of physiological time-series data collected from low-resource clinical settings limits the capabilities of modern machine learning algorithms in achieving high performance. Such performance is further hindered by class imbalance; datasets where a diagnosis is much more common than others. To overcome these two issues at low-cost while preserving privacy, data augmentation methods can be employed. In the time domain, the traditional method of time-warping could alter the underlying data distribution with detrimental consequences. This is prominent when dealing with physiological conditions that influence the frequency components of data. In this paper, we propose PlethAugment; three different conditional generative adversarial networks (CGANs) with an adapted diversity term for the generation of pathological photoplethysmogram (PPG) signals in order to boost medical classification performance. To evaluate and compare the GANs, we introduce a novel metric-agnostic method; the synthetic generalization curve. We validate this approach on two proprietary and two public datasets representing a diverse set of medical conditions. Compared to training on non-augmented class-balanced datasets, training on augmented datasets leads to an improvement of the AUROC by up to 29% when using cross validation. This illustrates the potential of the proposed CGANs to significantly improve classification performance.

Multi-Modal Diagnosis of Infectious Diseases in the Developing World.

In low and middle income countries, infectious diseases continue to have a significant impact, particularly amongst the poorest in society. Tetanus and hand foot and mouth disease (HFMD) are two such diseases and, in both, death is associated with autonomic nervous system dysfunction (ANSD). Currently, photoplethysmogram or electrocardiogram monitoring is used to detect deterioration in these patients, however expensive clinical monitors are often required. In this study, we employ low-cost and mobile wearable devices to collect patient vital signs unobtrusively; and we develop machine learning algorithms for automatic and rapid triage of patients that provide efficient use of clinical resources. Existing methods are mainly dependent on the prior detection of clinical features with limited exploitation of multi-modal physiological data. Moreover, the latest developments in deep learning (e.g. cross-domain transfer learning) have not been sufficiently applied for infectious disease diagnosis. In this paper, we present a fusion of multi-modal physiological data to predict the severity of ANSD with a hierarchy of resource-aware decision making. First, an on-site triage process is performed using a simple classifier. Second, personalised longitudinal modelling is employed that takes the previous states of the patient into consideration. We have also employed a spectrogram representation of the physiological waveforms to exploit existing networks for cross-domain transfer learning, which avoids the laborious and data intensive process of training a network from scratch. Results show that the proposed framework has promising potential in supporting severity grading of infectious diseases in low-resources settings, such as in the developing world.

Heart Rate Variability as an Indicator of Autonomic Nervous System Disturbance in Tetanus.

Autonomic nervous system dysfunction (ANSD) is a significant cause of mortality in tetanus. Currently, diagnosis relies on nonspecific clinical signs. Heart rate variability (HRV) may indicate underlying autonomic nervous system activity and represents a potentially valuable noninvasive tool for ANSD diagnosis in tetanus. HRV was measured from three 5-minute electrocardiogram recordings during a 24-hour period in a cohort of patients with severe tetanus, all receiving mechanical ventilation. HRV measurements from all subjects-five with ANSD (Ablett Grade 4) and four patients without ANSD (Ablett Grade 3)-showed HRV was lower than reported ranges for healthy individuals. Comparing different severities of tetanus, raw data for both time and frequency measurements of HRV were reduced in those with ANSD compared with those without. Differences were statistically significant in all except root mean square SD, indicating HRV may be a valuable tool in ANSD diagnosis.

Severity detection tool for patients with infectious disease.

Hand foot and mouth disease (HFMD) and tetanus are serious infectious diseases in low- and middle-income countries. Tetanus, in particular, has a high mortality rate and its treatment is resource-demanding. Furthermore, HFMD often affects a large number of infants and young children. As a result, its treatment consumes enormous healthcare resources, especially when outbreaks occur. Autonomic nervous system dysfunction (ANSD) is the main cause of death for both HFMD and tetanus patients. However, early detection of ANSD is a difficult and challenging problem. The authors aim to provide a proof-of-principle to detect the ANSD level automatically by applying machine learning techniques to physiological patient data, such as electrocardiogram waveforms, which can be collected using low-cost wearable sensors. Efficient features are extracted that encode variations in the waveforms in the time and frequency domains. The proposed approach is validated on multiple datasets of HFMD and tetanus patients in Vietnam. Results show that encouraging performance is achieved. Moreover, the proposed features are simple, more generalisable and outperformed the standard heart rate variability analysis. The proposed approach would facilitate both the diagnosis and treatment of infectious diseases in low- and middle-income countries, and thereby improve patient care.

Cardiovascular disease diagnosis using cross-domain transfer learning.

While cardiovascular diseases (CVDs) are commonly diagnosed by cardiologists via inspecting electrocardiogram (ECG) waveforms, these decisions can be supported by a data-driven approach, which may automate this process. An automatic diagnostic approach often employs hand-crafted features extracted from ECG waveforms. These features, however, do not generalise well, challenged by variation in acquisition settings such as sampling rate and mounting points. Existing deep learning (DL) approaches, on the other hand, extract features from ECG automatically but require construction of dedicated networks that require huge data and computational resource if trained from scratch. Here we propose an end-to-end trainable cross-domain transfer learning for CVD classification from ECG waveforms, by utilising existing vision-based CNN frameworks as feature extractors, followed by ECG feature learning layers. Because these frameworks are designed for image inputs, we employ a stacked spectrogram representation of multi-lead ECG waveforms as a preprocessing step. We also proposed a fusion of multiple ECG leads, using plausible stacking arrangements of the spectrograms, to encode their spatial relations. The proposed approach is validated on multiple ECG datasets and competitive performance is achieved.