Development and Prospective Validation of a Transparent Deep Learning Algorithm for Predicting Need for Mechanical Ventilation

Assessing Barriers to Implementation of Machine Learning and Artificial Intelligence-Based Tools in Critical Care: Web-Based Survey Study

BACKGROUND

Although there is considerable interest in machine learning (ML) and artificial intelligence (AI) in critical care, the implementation of effective algorithms into practice has been limited.

OBJECTIVE

We sought to understand physician perspectives of a novel intubation prediction tool. Further, we sought to understand health care provider and nonprovider perspectives on the use of ML in health care. We aim to use the data gathered to elucidate implementation barriers and determinants of this intubation prediction tool, as well as ML/AI-based algorithms in critical care and health care in general.

METHODS

We developed 2 anonymous surveys in Qualtrics, 1 single-center survey distributed to 99 critical care physicians via email, and 1 social media survey distributed via Facebook and Twitter with branching logic to tailor questions for providers and nonproviders. The surveys included a mixture of categorical, Likert scale, and free-text items. Likert scale means with SD were reported from 1 to 5. We used student t tests to examine the differences between groups. In addition, Likert scale responses were converted into 3 categories, and percentage values were reported in order to demonstrate the distribution of responses. Qualitative free-text responses were reviewed by a member of the study team to determine validity, and content analysis was performed to determine common themes in responses.

RESULTS

Out of 99 critical care physicians, 47 (48%) completed the single-center survey. Perceived knowledge of ML was low with a mean Likert score of 2.4 out of 5 (SD 0.96), with 7.5% of respondents rating their knowledge as a 4 or 5. The willingness to use the ML-based algorithm was 3.32 out of 5 (SD 0.95), with 75% of respondents answering 3 out of 5. The social media survey had 770 total responses with 605 (79%) providers and 165 (21%) nonproviders. We found no difference in providers' perceived knowledge based on level of experience in either survey. We found that nonproviders had significantly less perceived knowledge of ML (mean 3.04 out of 5, SD 1.53 vs mean 3.43, SD 0.941; P<.001) and comfort with ML (mean 3.28 out of 5, SD 1.02 vs mean 3.53, SD 0.935; P=.004) than providers. Free-text responses revealed multiple shared concerns, including accuracy/reliability, data bias, patient safety, and privacy/security risks.

CONCLUSIONS

These data suggest that providers and nonproviders have positive perceptions of ML-based tools, and that a tool to predict the need for intubation would be of interest to critical care providers. There were many shared concerns about ML/AI in health care elucidated by the surveys. These results provide a baseline evaluation of implementation barriers and determinants of ML/AI-based tools that will be important in their optimal implementation and adoption in the critical care setting and health care in general.

Graph-based Fusion Modeling and Explanation for Disease Trajectory Prediction

We propose a relational graph to incorporate clinical similarity between patients while building personalized clinical event predictors with a focus on hospitalized COVID-19 patients. Our graph formation process fuses heterogeneous data, i.e., chest X-rays as node features and non-imaging EHR for edge formation. While node represents a snap-shot in time for a single patient, weighted edge structure encodes complex clinical patterns among patients. While age and gender have been used in the past for patient graph formation, our method incorporates complex clinical history while avoiding manual feature selection. The model learns from the patient's own data as well as patterns among clinically-similar patients. Our visualization study investigates the effects of 'neighborhood' of a node on its predictiveness and showcases the model's tendency to focus on edge-connected patients with highly suggestive clinical features common with the node. The proposed model generalizes well by allowing edge formation process to adapt to an external cohort.

Role of Machine Learning Techniques to Tackle the COVID-19 Crisis: Systematic Review

BACKGROUND

SARS-CoV-2, the novel coronavirus responsible for COVID-19, has caused havoc worldwide, with patients presenting a spectrum of complications that have pushed health care experts to explore new technological solutions and treatment plans. Artificial Intelligence (AI)-based technologies have played a substantial role in solving complex problems, and several organizations have been swift to adopt and customize these technologies in response to the challenges posed by the COVID-19 pandemic.

OBJECTIVE

The objective of this study was to conduct a systematic review of the literature on the role of AI as a comprehensive and decisive technology to fight the COVID-19 crisis in the fields of epidemiology, diagnosis, and disease progression.

METHODS

A systematic search of PubMed, Web of Science, and CINAHL databases was performed according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify all potentially relevant studies published and made available online between December 1, 2019, and June 27, 2020. The search syntax was built using keywords specific to COVID-19 and AI.

RESULTS

The search strategy resulted in 419 articles published and made available online during the aforementioned period. Of these, 130 publications were selected for further analyses. These publications were classified into 3 themes based on AI applications employed to combat the COVID-19 crisis: Computational Epidemiology, Early Detection and Diagnosis, and Disease Progression. Of the 130 studies, 71 (54.6%) focused on predicting the COVID-19 outbreak, the impact of containment policies, and potential drug discoveries, which were classified under the Computational Epidemiology theme. Next, 40 of 130 (30.8%) studies that applied AI techniques to detect COVID-19 by using patients' radiological images or laboratory test results were classified under the Early Detection and Diagnosis theme. Finally, 19 of the 130 studies (14.6%) that focused on predicting disease progression, outcomes (ie, recovery and mortality), length of hospital stay, and number of days spent in the intensive care unit for patients with COVID-19 were classified under the Disease Progression theme.

CONCLUSIONS

In this systematic review, we assembled studies in the current COVID-19 literature that utilized AI-based methods to provide insights into different COVID-19 themes. Our findings highlight important variables, data types, and available COVID-19 resources that can assist in facilitating clinical and translational research.