Dataset Information

Complete and Resilient Documentation for Operational Medical Environments Leveraging Mobile Hands-free Technology in a Systems Approach: Experimental Study.

ABSTRACT:

Background

Prehospitalization documentation is a challenging task and prone to loss of information, as paramedics operate under disruptive environments requiring their constant attention to the patients.

Objective

The aim of this study is to develop a mobile platform for hands-free prehospitalization documentation to assist first responders in operational medical environments by aggregating all existing solutions for noise resiliency and domain adaptation.

Methods

The platform was built to extract meaningful medical information from the real-time audio streaming at the point of injury and transmit complete documentation to a field hospital prior to patient arrival. To this end, the state-of-the-art automatic speech recognition (ASR) solutions with the following modular improvements were thoroughly explored: noise-resilient ASR, multi-style training, customized lexicon, and speech enhancement. The development of the platform was strictly guided by qualitative research and simulation-based evaluation to address the relevant challenges through progressive improvements at every process step of the end-to-end solution. The primary performance metrics included medical word error rate (WER) in machine-transcribed text output and an F1 score calculated by comparing the autogenerated documentation to manual documentation by physicians.

Results

The total number of 15,139 individual words necessary for completing the documentation were identified from all conversations that occurred during the physician-supervised simulation drills. The baseline model presented a suboptimal performance with a WER of 69.85% and an F1 score of 0.611. The noise-resilient ASR, multi-style training, and customized lexicon improved the overall performance; the finalized platform achieved a medical WER of 33.3% and an F1 score of 0.81 when compared to manual documentation. The speech enhancement degraded performance with medical WER increased from 33.3% to 46.33% and the corresponding F1 score decreased from 0.81 to 0.78. All changes in performance were statistically significant (P<.001).

Conclusions

This study presented a fully functional mobile platform for hands-free prehospitalization documentation in operational medical environments and lessons learned from its implementation.

SUBMITTER: Woo M

PROVIDER: S-EPMC8548972 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Complete and Resilient Documentation for Operational Medical Environments Leveraging Mobile Hands-free Technology in a Systems Approach: Experimental Study.

Woo MinJae M Mishra Prabodh P Lin Ju J Kar Snigdhaswin S Deas Nicholas N Linduff Caleb C Niu Sufeng S Yang Yuzhe Y McClendon Jerome J Smith D Hudson DH Shelton Stephen L SL Gainey Christopher E CE Gerard William C WC Smith Melissa C MC Griffin Sarah F SF Gimbel Ronald W RW Wang Kuang-Ching KC

JMIR mHealth and uHealth 20211012 10

<h4>Background</h4>Prehospitalization documentation is a challenging task and prone to loss of information, as paramedics operate under disruptive environments requiring their constant attention to the patients.<h4>Objective</h4>The aim of this study is to develop a mobile platform for hands-free prehospitalization documentation to assist first responders in operational medical environments by aggregating all existing solutions for noise resiliency and domain adaptation.<h4>Methods</h4>The platf ...[more]

PMID: 34636729

Similar Datasets

Project description:Study objectiveElectronic health record implementation can improve care, but may also adversely affect emergency department (ED) efficiency. We examine how a custom, ED provider, electronic documentation system (eDoc), which replaced paper documentation, affects operational performance.MethodsWe analyzed retrospective operational data for 1-year periods before and after eDoc implementation in a single ED. We computed daily operational statistics, reflecting 60,870 pre- and 59,337 postimplementation patient encounters. The prespecified primary outcome was daily mean length of stay; secondary outcomes were daily mean length of stay for admitted and discharged patients and daily mean arrival time to disposition for admitted patients. We used a prespecified multiple regression model to identify differences in outcomes while controlling for prespecified confounding variables.ResultsThe unadjusted change in length of stay was 8.4 minutes; unadjusted changes in secondary outcomes were length of stay for admitted patients 11.4 minutes, length of stay for discharged patients 1.8 minutes, and time to disposition 1.8 minutes. With a prespecified regression analysis to control for variations in operational characteristics, there were significant increases in length of stay (6.3 minutes [95% confidence interval 3.5 to 9.1 minutes]) and length of stay for discharged patients (5.1 minutes [95% confidence interval 1.9 to 8.3 minutes]). There was no statistically significant change in length of stay for admitted patients or time to disposition.ConclusionIn our single-center study, the isolated implementation of eDoc was associated with increases in overall and discharge length of stay. Our findings suggest that a custom-designed electronic provider documentation may negatively affect ED throughput. Strategies to mitigate these effects, such as reducing documentation requirements or adding clinical staff, scribes, or voice recognition, would be a valuable area of future research.

Project description:Digital health development and use has been expansive and operationalized in a variety of settings and modalities around the world, including in low- and middle-income countries. Mobile applications have been developed for a variety of health professionals and frontline health workers including physicians, midwives, nurses, and community health workers. However, there are no published studies on the development and use of digital health related to human rights fieldwork and to our knowledge no mobile health platforms exist specifically for use by frontline health workers to forensically and clinically document sexual violence. We describe a participatory development and user design process with Congolese end-users of a novel human rights app for clinicians intended to standardize the documentation of sexual violence evidence for forensic and legal purposes, called MediCapt. The app, yet to be launched and still in the future proofing phase, has included several development phases: (1) initial needs assessment conducted in 2011, (2) prototype development and field-testing in 2014 with 8 Congolese physicians, (3) prototype refinement and field-testing in 2015 with 9 clinicians. Feedback from the first field-testing phase was incorporated into the design of the second prototype; key features that were added to MediCapt include the ability for users to take photographs and draw on a pictogram to include as part of the evidence package, as well as the ability to print a form with the completed data. Questionnaires and key-informant interviews during the second and third field-testing phases revealed overall positive attitudes about MediCapt, but multiple perceived and actual barriers to implementation were identified, from personal behaviors, such as individual clinicians' comfort with new technology, to more systemic and infrastructure factors, such as strong cultural preferences for print documentation of evidence and limited Internet connectivity. Next phases of development include consideration of patients' acceptance of this technology, how it actually fits in the clinical workflow, and testing of how to transfer the collected evidence to law enforcement and legal authorities. Ultimately, we plan on conducting a robust evaluation to assess effectiveness of the app on medical, legal, and human rights outcomes. We believe our experience of collecting data that will potentially serve as legal evidence broadens the traditional scope of digital health and crosses a wide range of fields including medical, technological, legal, and ethical, and thus propose refining and defining this unique field of exploration as mobile justice, or mJustice.

Project description:BackgroundThe 2017 Australian Digital Health Agency (ADHA) Strategy is based on the underlying assumption that digital technology in health care environments is ubiquitous. The ADHA Strategy views health professionals, especially nurses, as grappling with the complexity of installing and using digital technologies to facilitate personalized and sustainable person-centered care. Yet, ironically, the 2018 debate over how to enroll Australians into the national electronic health record system and its alteration from an opt-in to an opt-out model heightened public and professional concern over what constituted a "safe, seamless and secure" health information system. What can be termed a digital technology paradox has emerged where, although it is widely acknowledged that there are benefits from deploying and using digital technology in the workplace, the perception of risk renders it unavailable or inaccessible at point of care. The inability of nurses to legitimately access and use mobile technology is impeding the diffusion of digital technology in Australian health care environments and undermining the 2017 ADHA Strategy.ObjectiveThis study explored the nature and scope of usability of mobile technology at point of care, in order to understand how current governance structures impacted on access and use of digital technology from an organizational perspective.MethodsIndividual semistructured interviews were conducted with 6 representatives from professional nursing organizations. A total of 10 interview questions focused on factors that impacted the use of mobile technology for learning at point of care. Seven national organizations and 52 members from the Coalition of National Nursing and Midwifery Organisations were invited to participate. Interviews were recorded and transcribed verbatim. Data analysis was systematic and organized, consisting of trial coding; member checking was undertaken to ensure rigor. A codebook was developed to provide a framework for analysis to identify the themes latent in the transcribed data. Nurses as stakeholders emerged as a key theme.ResultsOut of 6 participants, 4 female (67%) and 2 male (33%) senior members of the nursing profession were interviewed. Each interview lasted between 17 and 54 minutes, which reflected the knowledge of participants regarding the topic of interest and their availability. Two subthemes, coded as ways of thinking and ways of acting, emerged from the open codes. Participants provided examples of the factors that impacted the capacity of nurses to adopt digital technology from an emic perspective. There were contributing factors that related to actions, including work-arounds, attentiveness, and experiences. Nurses also indicated that there were attitudes and influences that impacted thinking regarding access and use of mobile technology at point of care.ConclusionsNurses are inadequately prepared for the digital future that has now arrived in health care environments. Nurses do not perceive that they are leaders in decision making regarding digital technology adoption, nor are they able to facilitate digital literacy or model digital professionalism.

Project description:BackgroundTo further reduce malaria burden, identification of areas with highest burden for targeted interventions needs to occur. Routine health information has the potential to indicate where and when clinical malaria occurs the most. Developing countries mostly use paper-based data systems however they are error-prone as they require manual aggregation, tallying and transferring of data. Piloting was done using electronic data capture (EDC) with a cheap and user friendly software in rural Malawian primary healthcare setting to improve the quality of health records.MethodsAudit and feedback tools from the Joanna Briggs Institute (Practical Application of Clinical Evidence System and Getting Research into Practice) were used in four primary healthcare facilities. Using this approach, the best available evidence for a malaria information system (MIS) was identified. Baseline audit of the existing MIS was conducted in the facilities based on available best practice for MIS; this included ensuring data consistency and completeness in MIS by sampling 25 random records of malaria positive cases. Implementation of an adapted evidence-based EDC system using tablets on an OpenDataKit platform was done. An end line audit following implementation was then conducted. Users had interviews on experiences and challenges concerning EDC at the beginning and end of the survey.ResultsThe existing MIS was paper-based, occupied huge storage space, had some data losses due to torn out papers and were illegible in some facilities. The existing MIS did not have documentation of necessary parameters, such as malaria deaths and treatment within 14 days. Training manuals and modules were absent. One health centre solely had data completeness and consistency at 100% of the malaria-positive sampled records. Data completeness and consistency rose to 100% with readily available records containing information on recent malaria treatment. Interview findings at the end of the survey showed that EDC was acceptable among users and they agreed that the tablets and the OpenDataKit were easy to use, improved productivity and quality of care.ConclusionsImprovement of data quality and use in the Malawian rural facilities was achieved through the introduction of EDC using OpenDataKit. Health workers in the facilities showed satisfaction with the use of EDC.

Project description:BACKGROUND:Identifying scalable strategies for assessing fidelity is a key challenge in implementation science. However, for psychosocial interventions, the existing, reliable ways to test treatment fidelity quality are often labor intensive, and less burdensome strategies may not reflect actual clinical practice. Cognitive behavioral therapies (CBTs) provide clinicians with a set of effective core elements to help treat a multitude of disorders, which, evidence suggests, need to be delivered with fidelity to maximize potential client impact. The current "gold standard" for rating CBTs is rating recordings of therapy sessions, which is extremely time-consuming and requires a substantial amount of initial training. Although CBTs can vary based on the target disorder, one common element employed in most CBTs is the use of worksheets to identify specific behaviors and thoughts that affect a client's ability to recover. The present study will develop and evaluate an innovative new approach to rate CBT fidelity, by developing a universal CBT scoring system based on worksheets completed in therapy sessions. METHODS:To develop a scoring system for CBT worksheets, we will compile common CBT elements from a variety of CBT worksheets for a range of psychiatric disorders and create adherence and competence measures. We will collect archival worksheets from past studies to test the scoring system and assess test-retest reliability. To evaluate whether CBT worksheet scoring accurately reflects clinician fidelity, we will recruit clinicians who are engaged in a CBT for depression, anxiety, and/or posttraumatic stress disorder. Clinicians and clients will transmit routine therapy materials produced in session (e.g., worksheets, clinical notes, session recordings) to the study team after each session. We will compare observer-rated fidelity, clinical notes, and fidelity-rated worksheets to identify the most effective and efficient method to assess clinician fidelity. Clients will also be randomly assigned to either complete the CBT worksheets on paper forms or on a mobile application (app) to learn if worksheet format influences clinician and client experience or differs in terms of reflecting fidelity. DISCUSSION:Scoring fidelity using CBT worksheets may allow clinics to test fidelity in a short and effective manner, enhancing continuous quality improvement in the workplace. Clinicians and clinics can use such data to improve clinician fidelity in real time, leading to improved patient outcomes. TRIAL REGISTRATION:ClinicalTrials.gov NCT03479398 . Retrospectively registered March 20, 2018.

Dataset Information

Complete and Resilient Documentation for Operational Medical Environments Leveraging Mobile Hands-free Technology in a Systems Approach: Experimental Study.

Background

Objective

Methods

Results

Conclusions

Publications

Complete and Resilient Documentation for Operational Medical Environments Leveraging Mobile Hands-free Technology in a Systems Approach: Experimental Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets