Clustering Research Proposal Submissions to Understand the Unmet Needs of Military Clinicians.

INTRODUCTION: The Advanced Medical Technology Initiative (AMTI) program solicits research proposals for technology demonstrations and performance improvement projects in the domain of military medicine. Advanced Medical Technology Initiative is managed by the U.S. Army Telemedicine and Advanced Technology Research Center (TATRC). Advanced Medical Technology Initiative proposals span a wide range of topics, for example, treatment of musculoskeletal injury, application of virtual health technology, and demonstration of medical robots. The variety and distribution of central topics in these proposals (problems to be solved and technological solutions proposed) are not well characterized. Characterizing this content over time could highlight over- and under-served problem domains, inspire new technological applications, and inform future research solicitation efforts. METHODS AND MATERIALS: This research sought to analyze and categorize historic AMTI proposals from 2010 to 2022 (n = 825). The analysis focused specifically on the "Problem to Be Solved" and "Technology to Demonstrated" sections of the proposals, whose categorizations are referred to as "Problem-Sets" and Solution-Sets" (PS and SS), respectively. A semi-supervised document clustering process was applied independently to the two sections. The process consisted of three stages: (1) Manual Document Annotation-a sample of proposals were manually labeled along each thematic axis; (2) Clustering-semi-supervised clustering, informed by the manually annotated sample, was applied to the proposals to produce document clusters; (3) Evaluation and Selection-quantitative and qualitative means were used to evaluate and select an optimal cluster solution. The results of the clustering were then summarized and presented descriptively. RESULTS: The results of the clustering process identified 24 unique PS and 20 unique SS. The most prevalent PS were Musculoskeletal Injury (12%), Traumatic Injury (11%), and Healthcare Systems Optimization (11%). The most prevalent SS were Sensing and Imaging Technology (27%), Virtual Health (23%), and Physical and Virtual Simulation (11.5%). The most common problem-solution pair was Healthcare Systems Optimization-Virtual Health, followed by Musculoskeletal Injury-Sensing and Imaging Technology. The analysis revealed that problem-solution-set co-occurrences were well distributed throughout the domain space, demonstrating the variety of research conducted in this research domain. CONCLUSIONS: A semi-supervised document clustering approach was applied to a repository of proposals to partially automate the process of document annotation. By applying this process, we successfully extracted thematic content from the proposals related to problems to be addressed and proposed technological solutions. This analysis provides a snapshot of the research supply in the domain of military medicine over the last 12 years. Future work should seek to replicate and improve the document clustering process used. Future efforts should also be made to compare these results to actual published work in the domain of military medicine, revealing differences in demand for research as determined by funding and publishing decision-makers and supply by researchers.

Research proposal content extraction using natural language processing and semi-supervised clustering: A demonstration and comparative analysis.

Funding institutions often solicit text-based research proposals to evaluate potential recipients. Leveraging the information contained in these documents could help institutions understand the supply of research within their domain. In this work, an end-to-end methodology for semi-supervised document clustering is introduced to partially automate classification of research proposals based on thematic areas of interest. The methodology consists of three stages: (1) manual annotation of a document sample; (2) semi-supervised clustering of documents; (3) evaluation of cluster results using quantitative metrics and qualitative ratings (coherence, relevance, distinctiveness) by experts. The methodology is described in detail to encourage replication and is demonstrated on a real-world data set. This demonstration sought to categorize proposals submitted to the US Army Telemedicine and Advanced Technology Research Center (TATRC) related to technological innovations in military medicine. A comparative analysis of method features was performed, including unsupervised vs. semi-supervised clustering, several document vectorization techniques, and several cluster result selection strategies. Outcomes suggest that pretrained Bidirectional Encoder Representations from Transformers (BERT) embeddings were better suited for the task than older text embedding techniques. When comparing expert ratings between algorithms, semi-supervised clustering produced coherence ratings ~ 25% better on average compared to standard unsupervised clustering with negligible differences in cluster distinctiveness. Last, it was shown that a cluster result selection strategy that balances internal and external validity produced ideal results. With further refinement, this methodological framework shows promise as a useful analytical tool for institutions to unlock hidden insights from untapped archives and similar administrative document repositories. Supplementary Information: The online version contains supplementary material available at 10.1007/s11192-023-04689-3.

Advanced Digital Health Technologies for COVID-19 and Future Emergencies.

Background: Coronavirus disease 2019 (COVID-19) has led to a national health care emergency in the United States and exposed resource shortages, particularly of health care providers trained to provide critical or intensive care. This article describes how digital health technologies are being or could be used for COVID-19 mitigation. It then proposes the National Emergency Tele-Critical Care Network (NETCCN), which would combine digital health technologies to address this and future crises. Methods: Subject matter experts from the Society of Critical Care Medicine and the Telemedicine and Advanced Technology Research Center examined the peer-reviewed literature and science/technology news to see what digital health technologies have already been or could be implemented to (1) support patients while limiting COVID-19 transmission, (2) increase health care providers' capability and capacity, and (3) predict/prevent future outbreaks. Results: Major technologies identified included telemedicine and mobile care (for COVID-19 as well as routine care), tiered telementoring, telecritical care, robotics, and artificial intelligence for monitoring. Several of these could be assimilated to form an interoperable scalable NETCCN. NETCCN would assist health care providers, wherever they are located, by obtaining real-time patient and supplies data and disseminating critical care expertise. NETCCN capabilities should be maintained between disasters and regularly tested to ensure continual readiness. Conclusions: COVID-19 has demonstrated the impact of a large-scale health emergency on the existing infrastructures. Short term, an approach to meeting this challenge is to adopt existing digital health technologies. Long term, developing a NETCCN may ensure that the necessary ecosystem is available to respond to future emergencies.

Does Mobile Care ('mCare') Improve Quality of Life and Treatment Satisfaction Among Service Members Rehabilitating in the Community? Results from a 36-Wk, Randomized Controlled Trial.

Introduction: Research has shown that mobile phones can help with management of numerous health problems. As an adjunct to care management provided to injured service members rehabilitating in their communities, particularly those with mild traumatic brain injury (mTBI), post-traumatic stress (PTS), and/or behavioral health problems, the Army developed a mobile phone application called "mCare." This study examined whether service members who received mCare had higher well-being, were more satisfied with their care, and viewed mCare as a valuable part of their care management as compared with their counterparts who received standard care management alone, and whether those with mTBI, PTS, and/or behavioral health problems benefited differently from mCare. Materials and Methods: In-processing service members at four community-based warrior transition units were recruited for participation in a 36-wk, randomized, controlled trial and allocated to receive standard care management plus mCare (n = 95) or standard care management alone (n = 87). Participants in the mCare group received daily questionnaires, tips, and appointment reminders. All participants were asked to complete the General Well-being Schedule (GWS) at baseline, 12, 24, and 36 wk, and the Case Management Quality Questionnaire (CMQQ) at 12, 24, and 36 wk. All participants and care managers were approached to complete interviews about the usability/likeability of mCare or standard care management. The analyses tested for group differences in completion of the intervention, graphed means for the GWS and CMQQ by group/subgroup, and statistically compared the longitudinal trends in these outcomes using mixed models in which group, time, and group*time were included as regression variables. The analyses also tallied interview responses and identified thematic quotes. The study protocol was reviewed and approved by the Walter Reed National Military Medical Center's Institutional Review Board. Results: Estimated rate of change in GWS scores was -2.2 (standard error = 1.0; t = -2.1; p = 0.0382). Estimated rate of change in CMQQ scores was -0.8 (standard error = 0.5; t = -1.52; p = 0.1299). Neither change was meaningful. Rates of change in the GWS and CMQQ scores did not differ by group or by behavioral health, mTBI, and PTS subgroups within the groups. The interviews found that 83% of mCare participants liked the communication with their care managers versus 73% of standard care management participants. Participants in both the mCare group and the care managers said that they liked the application's appointment tracking and reminders. Care managers thought mCare was particularly useful for people with mTBI, PTS, and cognitive problems. Conclusion: mCare did not result in differences in general well-being and satisfaction with care management among service members rehabilitating in their communities, some with mTBI, PTS, and/or behavioral health problems. But participants and care managers who used mCare said that they found it useful. Study limitations included the diversity of clinical issues of the participants, greater missing data among mCare participants, and the high baseline quality of care management in the settings observed. The fact that patients and care managers liked mCare, apart from no changes in outcomes, is important because health care is increasingly adopting mobile solutions.

mCare: using secure mobile technology to support soldier reintegration and rehabilitation.

BACKGROUND: The U.S. Army Medical Department conducted a pilot mobile health project to determine the requirements for coordination of care for "Wounded Warriors" using mobile messaging. The primary objective was to determine if a secure mobile health (mhealth) intervention provided to geographically dispersed patients would improve contact rates and positively impact the military healthcare system. METHODS AND MATERIALS: Over 21 months, volunteers enrolled in a Health Insurance Portability and Accountability Act-compliant, secure mobile messaging initiative called mCare. The study included males and females, 18-61 years old, with a minimum of 60 days of outpatient recovery. Volunteers were required to have a compatible phone. The mhealth intervention included appointment reminders, health and wellness tips, announcements, and other relevant information to this population exchanged between care teams and patients. RESULTS: Provider respondents reported that 85% would refer patients to mCare, and 56% noted improvement in appointment attendance (n=90). Patient responses also revealed high acceptability of mCare and refined the frequency and delivery times (n=114). The pilot project resulted in over 84,000 outbound messages and improved contact rates by 176%. CONCLUSIONS: The mCare pilot project demonstrated the feasibility and administrative effectiveness of a scalable mhealth application using secure mobile messaging and information exchanges, including personalized patient education.