An automated COVID-19 triage pipeline using artificial intelligence based on chest radiographs and clinical data

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital’s image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.

Non-contact physiological monitoring of post-operative patients in the intensive care unit

Prolonged non-contact camera-based monitoring in critically ill patients presents unique challenges, but may facilitate safe recovery. A study was designed to evaluate the feasibility of introducing a non-contact video camera monitoring system into an acute clinical setting. We assessed the accuracy and robustness of the video camera-derived estimates of the vital signs against the electronically-recorded reference values in both day and night environments. We demonstrated non-contact monitoring of heart rate and respiratory rate for extended periods of time in 15 post-operative patients. Across day and night, heart rate was estimated for up to 53.2% (103.0 h) of the total valid camera data with a mean absolute error (MAE) of 2.5 beats/min in comparison to two reference sensors. We obtained respiratory rate estimates for 63.1% (119.8 h) of the total valid camera data with a MAE of 2.4 breaths/min against the reference value computed from the chest impedance pneumogram. Non-contact estimates detected relevant changes in the vital-sign values between routine clinical observations. Pivotal respiratory events in a post-operative patient could be identified from the analysis of video-derived respiratory information. Continuous vital-sign monitoring supported by non-contact video camera estimates could be used to track early signs of physiological deterioration during post-operative care.

Digital health tools for the passive monitoring of depression: a systematic review of methods

The use of digital tools to measure physiological and behavioural variables of potential relevance to mental health is a growing field sitting at the intersection between computer science, engineering, and clinical science. We summarised the literature on remote measuring technologies, mapping methodological challenges and threats to reproducibility, and identified leading digital signals for depression. Medical and computer science databases were searched between January 2007 and November 2019. Published studies linking depression and objective behavioural data obtained from smartphone and wearable device sensors in adults with unipolar depression and healthy subjects were included. A descriptive approach was taken to synthesise study methodologies. We included 51 studies and found threats to reproducibility and transparency arising from failure to provide comprehensive descriptions of recruitment strategies, sample information, feature construction and the determination and handling of missing data. The literature is characterised by small sample sizes, short follow-up duration and great variability in the quality of reporting, limiting the interpretability of pooled results. Bivariate analyses show consistency in statistically significant associations between depression and digital features from sleep, physical activity, location, and phone use data. Machine learning models found the predictive value of aggregated features. Given the pitfalls in the combined literature, these results should be taken purely as a starting point for hypothesis generation. Since this research is ultimately aimed at informing clinical practice, we recommend improvements in reporting standards including consideration of generalisability and reproducibility, such as wider diversity of samples, thorough reporting methodology and the reporting of potential bias in studies with numerous features.

Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review

While the opportunities of ML and AI in healthcare are promising, the growth of complex data-driven prediction models requires careful quality and applicability assessment before they are applied and disseminated in daily practice. This scoping review aimed to identify actionable guidance for those closely involved in AI-based prediction model (AIPM) development, evaluation and implementation including software engineers, data scientists, and healthcare professionals and to identify potential gaps in this guidance. We performed a scoping review of the relevant literature providing guidance or quality criteria regarding the development, evaluation, and implementation of AIPMs using a comprehensive multi-stage screening strategy. PubMed, Web of Science, and the ACM Digital Library were searched, and AI experts were consulted. Topics were extracted from the identified literature and summarized across the six phases at the core of this review: (1) data preparation, (2) AIPM development, (3) AIPM validation, (4) software development, (5) AIPM impact assessment, and (6) AIPM implementation into daily healthcare practice. From 2683 unique hits, 72 relevant guidance documents were identified. Substantial guidance was found for data preparation, AIPM development and AIPM validation (phases 1–3), while later phases clearly have received less attention (software development, impact assessment and implementation) in the scientific literature. The six phases of the AIPM development, evaluation and implementation cycle provide a framework for responsible introduction of AI-based prediction models in healthcare. Additional domain and technology specific research may be necessary and more practical experience with implementing AIPMs is needed to support further guidance.

The language of crisis: spatiotemporal effects of COVID-19 pandemic dynamics on health crisis communications by political leaders

In times of crisis, communication by leaders is essential for mobilizing an effective public response. During the COVID-19 pandemic, compliance with public health guidelines has been critical for the prevention of infections and deaths. We assembled a corpus of over 1500 pandemic-related speeches, containing over 4 million words, delivered by all 50 US state governors during the initial months of the COVID-19 pandemic. We analyzed the semantic, grammatical and linguistic-complexity properties of these speeches, and examined their relationships to COVID-19 case rates over space and time. We found that as COVID-19 cases rose, governors used stricter language to issue guidance, employed greater negation to defend their actions and highlight prevailing uncertainty, and used more extreme descriptive adjectives. As cases surged to their highest levels, governors used shorter words with fewer syllables. Investigating and understanding such characteristic responses to stress is important for improving effective public communication during major health crises.

Predicting changes in glycemic control among adults with prediabetes from activity patterns collected by wearable devices

The use of wearables is increasing and data from these devices could improve the prediction of changes in glycemic control. We conducted a randomized trial with adults with prediabetes who were given either a waist-worn or wrist-worn wearable to track activity patterns. We collected baseline information on demographics, medical history, and laboratory testing. We tested three models that predicted changes in hemoglobin A1c that were continuous, improved glycemic control by 5% or worsened glycemic control by 5%. Consistently in all three models, prediction improved when (a) machine learning was used vs. traditional regression, with ensemble methods performing the best; (b) baseline information with wearable data was used vs. baseline information alone; and (c) wrist-worn wearables were used vs. waist-worn wearables. These findings indicate that models can accurately identify changes in glycemic control among prediabetic adults, and this could be used to better allocate resources and target interventions to prevent progression to diabetes.

Prediction across healthcare settings: a case study in predicting emergency department disposition

Several approaches exist today for developing predictive models across multiple clinical sites, yet there is a lack of comparative data on their performance, especially within the context of EHR-based prediction models. We set out to provide a framework for prediction across healthcare settings. As a case study, we examined an ED disposition prediction model across three geographically and demographically diverse sites. We conducted a 1-year retrospective study, including all visits in which the outcome was either discharge-to-home or hospitalization. Four modeling approaches were compared: a ready-made model trained at one site and validated at other sites, a centralized uniform model incorporating data from all sites, multiple site-specific models, and a hybrid approach of a ready-made model re-calibrated using site-specific data. Predictions were performed using XGBoost. The study included 288,962 visits with an overall admission rate of 16.8% (7.9–26.9%). Some risk factors for admission were prominent across all sites (e.g., high-acuity triage emergency severity index score, high prior admissions rate), while others were prominent at only some sites (multiple lab tests ordered at the pediatric sites, early use of ECG at the adult site). The XGBoost model achieved its best performance using the uniform and site-specific approaches (AUC = 0.9–0.93), followed by the calibrated-model approach (AUC = 0.87–0.92), and the ready-made approach (AUC = 0.62–0.85). Our results show that site-specific customization is a key driver of predictive model performance.

Smartphone-based digital phenotyping for dry eye toward P4 medicine: a crowdsourced cross-sectional study

Multidimensional integrative data analysis of digital phenotyping is crucial for elucidating the pathologies of multifactorial and heterogeneous diseases, such as the dry eye (DE). This crowdsourced cross-sectional study explored a novel smartphone-based digital phenotyping strategy to stratify and visualize the heterogenous DE symptoms into distinct subgroups. Multidimensional integrative data were collected from 3,593 participants between November 2016 and September 2019. Dimension reduction via Uniform Manifold Approximation and Projection stratified the collected data into seven clusters of symptomatic DE. Symptom profiles and risk factors in each cluster were identified by hierarchical heatmaps and multivariate logistic regressions. Stratified DE subgroups were visualized by chord diagrams, co-occurrence networks, and Circos plot analyses to improve interpretability. Maximum blink interval was reduced in clusters 1, 2, and 5 compared to non-symptomatic DE. Clusters 1 and 5 had severe DE symptoms. A data-driven multidimensional analysis with digital phenotyping may establish predictive, preventive, personalized, and participatory medicine.

Randomized trial of two artificial intelligence coaching interventions to increase physical activity in cancer survivors

Physical activity (PA) has numerous health benefits. Personalized coaching may increase adherence to PA recommendations, but it is challenging to deliver personalized coaching in a scalable manner. The objective of our study was to determine whether novel artificially intelligent (AI) coaching interventions increase PA among overweight or obese, physically inactive cancer survivors compared to a control arm that receives health information. We conducted a single-center, three-arm randomized trial with equal allocation to (1) voice-assisted AI coaching delivered by smart speaker (MyCoach), (2) autonomous AI coaching delivered by text message (SmartText), and (3) control. Data collection was automated via sensors and voice technology, effectively masking outcome ascertainment. The primary outcome was change in mean steps per day from baseline to the end of follow-up at 4 weeks. Of the 42 randomized participants, 91% were female, and 36% were Black; mean age was 62.1 years, and mean BMI was 32.9 kg/m2. The majority were breast cancer survivors (85.7%). At the end of 4 weeks follow-up, steps increased in the MyCoach arm by an average of 3618.2 steps/day; the net gain in this arm was significantly greater [net difference = 3568.9 steps/day (95% CI: 1483–5655), P value <0.001] compared to control arm, and [net difference = 2160.6 steps/day (95% CI: 11–4310), P value 0.049] compared to SmartText. In conclusion, AI-based voice-assisted coaching shows promise as a practical method of delivering scalable, individualized coaching to increase physical activity in sedentary cancer survivors. Additional research is needed to replicate these findings in a broader population of cancer survivors and to investigate the effects of these interventions in the general population.ClinicalTrials.gov Identifier: NCT03212079, July 11, 2017, https://clinicaltrials.gov/ct2/show/NCT03212079.

Broadening the reach of the FDA Sentinel system: A roadmap for integrating electronic health record data in a causal analysis framework

The Sentinel System is a major component of the United States Food and Drug Administration’s (FDA) approach to active medical product safety surveillance. While Sentinel has historically relied on large quantities of health insurance claims data, leveraging longitudinal electronic health records (EHRs) that contain more detailed clinical information, as structured and unstructured features, may address some of the current gaps in capabilities. We identify key challenges when using EHR data to investigate medical product safety in a scalable and accelerated way, outline potential solutions, and describe the Sentinel Innovation Center’s initiatives to put solutions into practice by expanding and strengthening the existing system with a query-ready, large-scale data infrastructure of linked EHR and claims data. We describe our initiatives in four strategic priority areas: (1) data infrastructure, (2) feature engineering, (3) causal inference, and (4) detection analytics, with the goal of incorporating emerging data science innovations to maximize the utility of EHR data for medical product safety surveillance.