RESUMEN
The promise of artificial intelligence (AI) has generated enthusiasm among patients, healthcare professionals, and technology developers who seek to leverage its potential to enhance the diagnosis and management of an increasing number of chronic and acute conditions. Point-of-care testing (POCT) increases access to care because it enables care outside of traditional medical settings. Collaboration among developers, clinicians, and end users is an effective best practice for solving clinical problems. A common set of clearly defined terms that are easily understood by research teams is a valuable tool that fosters these collaborations. We present brief, accurate, and clear descriptions of terms and techniques used to develop new device and decision support technologies in association with their most common applications to POCT. This lexicon of terms used to describe AI and machine learning techniques is quick reference for healthcare professionals, researchers, developers, and patients. Commonly used methods and techniques are tabulated and presented with text providing the context of their common usage and required data characteristics. Finally, we summarize model effectiveness measurement and the assessment of component features contributions. Artificial intelligence (AI) refers to non-human techniques that infer meaning from sets of data. It can produce generalizations, classifications, predictions, and can identify associations using automated learning methods. This guide provides an overview of these methods and their application to point-of-care testing.
RESUMEN
Background: The use of point-of-care (POC) tests prior to the COVID-19 pandemic was relatively infrequent outside of the health care context. Little is known about how public opinions regarding POC tests have changed during the pandemic. Methods: We redeployed a validated survey to uncompensated volunteers to assess preferences for point-of-care testing (POCT) benefits and concerns between June and September 2022. We received a total of 292 completed surveys. Linear regression analysis was used to compare differences in survey average response scores (ARSs) from 2020 to 2022. Results: Respondent ARSs indicated agreement for all 16 POCT benefits in 2022. Of 14 POCT concerns, there were only 2 statements that respondents agreed with most frequently, which were that "Insurance might not cover the costs of the POC test" (ARS 0.9, ± 1.0) and "POC tests might not provide a definitive result" (ARS 0.1, ± 1.0). Additionally, when comparing survey responses from 2020 to 2022, we observed 8 significant trends for POCT harms and benefits. Conclusion: The public's opinion on POC tests has become more favorable over time. However, concerns regarding the affordability and reliability of POCT results persist. We suggest that stakeholders address these concerns by developing accurate POC tests that continue to improve care and facilitate access to health care for all.
RESUMEN
Point-of-care technology (POCT) plays a vital role in modern healthcare by providing a fast diagnosis, improving patient management, and extending healthcare access to remote and resource-limited areas. The objective of this study was to understand how healthcare professionals in the United States perceived POCTs during 2019-2021 to assess the decision-making process of implementing these newer technologies into everyday practice. A 5-point Likert scale survey was sent to respondents to evaluate their perceptions of benefits, concerns, characteristics, and development of point-of-care technologies. The 2021 survey was distributed November 1st, 2021- February 15th, 2022, with a total of 168 independent survey responses received. Of the respondents, 59% identified as male, 73% were white, and 48% have been in practice for over 20 years. The results showed that most agreed that POCTs improve patient management (94%) and improve clinician confidence in decision making (92%). Healthcare professionals were most concerned with potentially not being reimbursed for the cost of the POCT (37%). When asked to rank the top 3 important characteristics of POCT, respondents chose accuracy, ease of use, and availability. It is important to note this survey was conducted during the COVID-19 pandemic. To achieve an even greater representation of healthcare professionals' point of view on POCTs, further work to obtain responses from a larger, more diverse population of providers is needed.
Asunto(s)
Pandemias , Sistemas de Atención de Punto , Humanos , Masculino , Personal de Salud , Atención a la Salud , Encuestas y CuestionariosRESUMEN
BACKGROUND: Machine learning (ML)-derived notifications for impending episodes of hemodynamic instability and respiratory failure events are interesting because they can alert physicians in time to intervene before these complications occur. RESEARCH QUESTION: Do ML alerts, telemedicine system (TS)-generated alerts, or biomedical monitors (BMs) have superior performance for predicting episodes of intubation or administration of vasopressors? STUDY DESIGN AND METHODS: An ML algorithm was trained to predict intubation and vasopressor initiation events among critically ill adults. Its performance was compared with BM alarms and TS alerts. RESULTS: ML notifications were substantially more accurate and precise, with 50-fold lower alarm burden than TS alerts for predicting vasopressor initiation and intubation events. ML notifications of internal validation cohorts demonstrated similar performance for independent academic medical center external validation and COVID-19 cohorts. Characteristics were also measured for a control group of recent patients that validated event detection methods and compared TS alert and BM alarm performance. The TS test characteristics were substantially better, with 10-fold less alarm burden than BM alarms. The accuracy of ML alerts (0.87-0.94) was in the range of other clinically actionable tests; the accuracy of TS (0.28-0.53) and BM (0.019-0.028) alerts were not. Overall test performance (F scores) for ML notifications were more than fivefold higher than for TS alerts, which were higher than those of BM alarms. INTERPRETATION: ML-derived notifications for clinically actioned hemodynamic instability and respiratory failure events represent an advance because the magnitude of the differences of accuracy, precision, misclassification rate, and pre-event lead time is large enough to allow more proactive care and has markedly lower frequency and interruption of bedside physician work flows.
RESUMEN
BACKGROUND: The evolving opinions of our community members provide insights into how end-users perceive the value and identify key point-of-care test (POCT) characteristics. METHODS: We deployed our validated 45-item English-language survey to uncompensated volunteers and compared the results from 1264 respondents in 2021 with those obtained in 2020. RESULTS: Average responses for items regarding the benefits of POCTs demonstrated that the 2021 respondents indicated agreement with all 14 potential benefits. Average responses for items regarding concerns were distinctly different from those for benefits. The only concern item that scored in the agree range was "not having insurance coverage for POCTs." Average responses to the other 13 concern items were in the disagree range. For 8 of these items, the magnitude of disagreement was greater in the 2021 survey than was observed for the 2020 survey. Differences in POCT exposure over time and by US regions suggest that higher levels of exposure to POCTs in the East are associated with stronger public support. CONCLUSIONS: Community members strongly support the development of accurate, convenient, easy-to-use, affordable, equitably available, in-home POCTs that produce immediate results. This empowers patients and home caregivers to diagnose, manage, enhance their adherence to medical treatments, and more efficiently engage their physicians.
Asunto(s)
Prioridad del Paciente , Médicos , Humanos , Pruebas en el Punto de Atención , Encuestas y CuestionariosRESUMEN
The concept of telecritical care has evolved over several decades. ICU Telemedicine providers using both the hub-and-spoke ICU telemedicine center and consultative service delivery models offered their services during the COVID-19 pandemic. Telemedicine center responses were more efficient, timely, and widely used than those of the consultative model. Bedside nurses, physicians, nurse practitioners, physician assistants, and respiratory therapists incorporated the use of ICU telemedicine tools into their practices and more frequently requested critical care specialist telemedicine support.
Asunto(s)
COVID-19 , Telemedicina , Cuidados Críticos , Humanos , Unidades de Cuidados Intensivos , PandemiasRESUMEN
The COVID-19 pandemic offers a unique context and opportunity to investigate changes in healthcare professional perceptions towards the adoption of novel medical technologies, such as point-of-care technologies (POCTs). POCTs are a nascent technology that has experienced rapid growth as a result of COVID-19 due to their ability to increase healthcare accessibility via near-patient delivery, including at-home. We surveyed healthcare professionals before and during COVID-19 to explore whether the pandemic altered their perceptions about the usefulness of POCTs. Our network analysis method provided a structure for understanding this changing phenomenon. We uncovered that POCTs are not only useful for diagnosing COVID-19, but healthcare professionals also perceive them as increasingly important for diagnosing other diseases, such as cardiovascular, endocrine, respiratory, and metabolic diseases. Healthcare professionals also viewed POCTs as facilitating the humanization of epidemiology by improving disease management/monitoring and strengthening the clinician-patient relationship. As the accuracy and integration of these technologies into mainstream healthcare delivery improves, hurdles to their adoption dissipate, thereby encouraging healthcare professionals to rely upon them more frequently to diagnose, manage, and monitor diseases. The technological advances made in POCTs during COVID-19, combined with shifting positive perceptions of their utility by healthcare professionals, may better prepare us for the next pandemic.
RESUMEN
Point-of-care testing (POCT) is an emerging technology that provides crucial assistance in delivering healthcare. The COVID-19 pandemic led to the accelerated importance of POCT technology due to its in-home accessibility. While POCT use and implementation has increased, little research has been published about how healthcare professionals perceive these technologies. The objective of our study was to examine the current perspectives of healthcare professionals towards POCT. We surveyed healthcare professionals to quantify perceptions of POCT usage, adoption, benefits, and concerns between October 2020 and November 2020. Questions regarding POCT perception were assessed on a 5-point Likert Scale. We received a total of 287 survey responses. Of the respondents, 53.7% were male, 66.6% were white, and 30.7% have been in practice for over 20 years. We found that the most supported benefit was POCTs ability to improve patient management (92%) and that the most supported concern was that POCTs lead to over-testing (30%). This study provides a better understanding of healthcare workers' perspectives on POCT. To improve patient outcomes through the usage of POCT, greater research is needed to assess the needs and concerns of industry and healthcare stakeholders.
RESUMEN
OBJECTIVES: The Society of Critical Care Medicine convened its Academic Leaders in Critical Care Medicine taskforce on February 22, 2016, during the 45th Critical Care Congress to develop a series of consensus papers with toolkits for advancing critical care organizations in North America. The goal of this article is to propose a framework based on the expert opinions of critical care organization leaders and their responses to a survey, for current and future critical care organizations, and their leadership in the health system to design and implement successful regionalization for critical care in their regions. DATA SOURCES AND STUDY SELECTION: Members of the workgroup convened monthly via teleconference with the following objectives: to 1) develop and analyze a regionalization survey tool for 23 identified critical care organizations in the United States, 2) assemble relevant medical literature accessed using Medline search, 3) use a consensus of expert opinions to propose the framework, and 4) create groups to write the subsections and assemble the final product. DATA EXTRACTION AND SYNTHESIS: The most prevalent challenges for regionalization in critical care organizations remain a lack of a strong central authority to regulate and manage the system as well as a lack of necessary infrastructure, as described more than a decade ago. We provide a framework and outline a nontechnical approach that the health system and their critical care medicine leadership can adopt after considering their own structure, complexity, business operations, culture, and the relationships among their individual hospitals. Transforming the current state of regionalization into a coordinated, accountable system requires a critical assessment of administrative and clinical challenges and barriers. Systems thinking, business planning and control, and essential infrastructure development are critical for assisting critical care organizations. CONCLUSIONS: Under the value-based paradigm, the goals are operational efficiency and patient outcomes. Health systems that can align strategy and operations to assist the referral hospitals with implementing regionalization will be better positioned to regionalize critical care effectively.
Asunto(s)
Cuidados Críticos/organización & administración , Planificación de Instituciones de Salud/organización & administración , Eficiencia Organizacional , Humanos , Liderazgo , Derivación y Consulta/organización & administración , Análisis de Sistemas , Telemedicina/organización & administración , Resultado del Tratamiento , Estados UnidosRESUMEN
OBJECTIVE: Predictive models for critical events in the intensive care unit (ICU) might help providers anticipate patient deterioration. At the heart of predictive model development lies the ability to accurately label significant events, thereby facilitating the use of machine learning and similar strategies. We conducted this study to establish the validity of an automated system for tagging respiratory and hemodynamic deterioration by comparing automatic tags to tagging by expert reviewers. METHODS: This retrospective cohort study included 72,650 unique patient stays collected from Electronic Medical Records of the University of Massachusetts' eICU. An enriched subgroup of stays was manually tagged by expert reviewers. The tags generated by the reviewers were compared to those generated by an automated system. RESULTS: The automated system was able to rapidly and efficiently tag the complete database utilizing available clinical data. The overall agreement rate between the automated system and the clinicians for respiratory and hemodynamic deterioration tags was 89.4% and 87.1%, respectively. The automatic system did not add substantial variability beyond that seen among the reviewers. CONCLUSIONS: We demonstrated that a simple rule-based tagging system could provide a rapid and accurate tool for mass tagging of a compound database. These types of tagging systems may replace human reviewers and save considerable resources when trying to create a validated, labeled database used to train artificial intelligence algorithms. The ability to harness the power of artificial intelligence depends on efficient clinical validation of targeted conditions; hence, these systems and the methodology used to validate them are crucial.
RESUMEN
The commercialization of medical devices and biotechnology products is characterized by high failure rates and long development lead times particularly among start-up enterprises. To increase the success rate of these high-risk ventures, the University of Massachusetts Lowell (UML) and University of Massachusetts Medical School (UMMS) partnered to create key academic support centers with programs to accelerate entrepreneurship and innovation in this industry. In 2008, UML and UMMS founded the Massachusetts Medical Device Development Center (M2D2), which is a business and technology incubator that provides business planning, product prototyping, laboratory services, access to clinical testing, and ecosystem networking to medical device and biotech start-up firms. M2D2 has three physical locations that encompass approximately 40,000 square feet. Recently, M2D2 leveraged these resources to expand into new areas such as health security, point of care technologies for heart, lung, blood, and sleep disorders, and rapid diagnostics to detect SARS-CoV-2. Since its inception, M2D2 has vetted approximately 260 medical device and biotech start-up companies for inclusion in its programs and provided active support to more than 80 firms. This manuscript describes how two UMass campuses leveraged institutional, state, and Federal resources to create a thriving entrepreneurial environment for medical device and biotech companies.
RESUMEN
Background: Point-of-care testing (POCT) has applications across medical specialties and holds promise to improve patient care. While cardiovascular medicine has been attractive for POCT applications in recent years, little is known about how cardiovascular health professionals perceive them. Objective: The objective of our study was to examine differences in perceptions and attitudes towards POCTs between cardiovascular health professionals compared to other healthcare professionals. Methods: We surveyed healthcare professionals to assess perceptions of POCT usage and their benefits and concerns between October 2019 and March 2020. Questions regarding POCT perceptions were assessed on a 5-point Likert scale. Results: We received a total of 148 survey responses; of the responders, 52% were male, 59% were physicians, and 50% worked in a hospital setting. We found that cardiology professionals were less likely, compared to other specialties, to view POCTs as improving patient management or reducing errors. These cardiology professionals were not constrained by resources or a lack of investment opportunities to implement these technologies. Conclusion: This study provides a better understanding of perceptions about POCTs among healthcare specialists. To improve patient outcomes through the adoption and usage of POCTs, greater collaboration is advised among key industry and healthcare stakeholders.
RESUMEN
OBJECTIVES: This report provides analyses and perspective of a survey of critical care workforce, workload, and burnout among the intensivists and advanced practice providers of established U.S. and Canadian critical care organizations and provides a research agenda. DESIGN: A 97-item electronic survey questionnaire was distributed to the leaders of 27 qualifying organizations. SETTING: United States and Canada. PARTICIPANTS: Leaders of critical care organizations in the United States and Canada. INTERVENTIONS: None. DATA SYNTHESIS AND MAIN RESULTS: We received 23 responses (85%). The critical care organization survey recorded substantial variability of most organizational aspects that were not restricted by the critical care organization definition or regulatory mandates. The most common physician staffing model was a combination of full-time and part-time intensivists. Approximately 80% of critical care organizations had dedicated advanced practice providers that staffed some or all their ICUs. Full-time intensivists worked a median of 168 days (range 42-192 d) in the ICU (168 shifts = 24 7-d wk). The median shift duration was 12 hours (range, 7-14 hr), and the median number of consecutive shifts allowed was 7 hours (range 7-14 hr). More than half of critical care organizations reported having burnout prevention programs targeted to ICU physicians, advanced practice providers, and nurses. CONCLUSIONS: The variability of current approaches suggests that systematic comparative analyses could identify best organizational practices. The research agenda for the study of critical care organizations should include studies that provide insights regarding the effects of the integrative structure of critical care organizations on outcomes at the levels of our patients, our workforce, our work practices, and sustainability.
Asunto(s)
Agotamiento Profesional/epidemiología , Cuidados Críticos/estadística & datos numéricos , Fuerza Laboral en Salud/estadística & datos numéricos , Carga de Trabajo/estadística & datos numéricos , Adulto , Investigación Biomédica/métodos , Agotamiento Profesional/etiología , Canadá/epidemiología , Cuidados Críticos/organización & administración , Enfermedad Crítica/epidemiología , Fuerza Laboral en Salud/organización & administración , Humanos , Persona de Mediana Edad , Encuestas y Cuestionarios , Estados Unidos/epidemiología , Carga de Trabajo/psicologíaRESUMEN
Exposure to vaping is associated with a growing list of respiratory syndromes including an acute progressive form with life-threatening hypoxemic respiratory failure and pathologic changes of lung injury termed vaping-associated respiratory distress syndrome. DATA SOURCES: Center from Disease Control, Departments of Public Health, MEDLINE (via PubMed), and the Cochrane Library. STUDY SELECTION DATA EXTRACTION AND DATA SYNTHESIS: Cases, series, and public health reports of cases that met the Centers for Disease Control and Prevention case definition of vaping-associated respiratory disease were extracted by an author with perfect verification by a second. Cases were classified on the basis of toxin exposure, symptoms, oxygen saturation, progression to respiratory failure, and pathologic features, and a clinically actionable system of classification was based on expert opinion. CONCLUSIONS: The reported spectrum of vaping-associated respiratory diseases allows clinical classification of cases into groups with distinct evaluation, management, and recommendations for prevention and follow-up. Clinical stratification also identifies a small proportion of vaping-exposed patients who are at risk for progression to hypoxemic respiratory failure and an acute respiratory distress syndrome-like illness.
RESUMEN
BACKGROUND: Studies of current opinion of our community members for the characteristics, mode, and location of use, use cases, and overall enthusiasm for point-of-care testing (POCT) diagnosis and management tools are needed. STUDY DESIGN AND METHODS: Qualitative research methods were used to develop, refine, and evaluate hardcopy and electronic versions of a 45-item English language survey. The accuracy of the instrument was measured by recorded structured interview, and its precision was measured by comparison to its administration to a group of uncompensated volunteers. MAIN FINDINGS AND RESULTS: Comparison of survey and structured interview data demonstrated high levels of accuracy. Highly concordant with significant levels of correlation and of direct association indicated favorable precision. Ninety-three percent of respondents believed that POCT could improve their care, and 56% identified having a POCT in their home as a top priority. Accuracy, insurance coverage, immediacy of results, and ease of use were identified as the most important characteristics of a POCT. CONCLUSIONS: Community members strongly support the development of accurate, in-home devices that produce immediate results that can be used to diagnose, manage, and encourage their adherence to treatments for their medical conditions.
RESUMEN
OBJECTIVE: To determine whether patients transfused red blood cell (RBC) products according to guideline-specified pretransfusion hemoglobin (Hb) concentrations or for other reasons were more likely to survive their intensive care unit (ICU) stay. DESIGN: An observational study of 375 478 episodes of ICU care, over 5 years, was performed with ICU survival as the primary outcome. Outcomes were analyzed as a function of pretransfusion Hb concentration for groups with distinct transfusion indications while adjusting for potential confounders. SETTING AND PATIENTS: This study included all adult patients discharged from 1 of 203 adult ICUs from 32 US health-care systems. The patients were from community hospitals, tertiary, and academic medical centers. INTERVENTION: Transfusion of allogenic packed RBCs or whole blood was prescribed at the discretion of the treating clinicians. MEASUREMENTS AND MAIN RESULTS: We found that 15% of adult ICU patients are transfused RBC products, and most transfusions for hemodynamically stable patients are administered above the guideline-specified pretransfusion Hb threshold of 7 g/dL. Hemodynamically stable patients transfused below this threshold were significantly more likely to survive their ICU stay than those not transfused (odds ratio [OR] 0.59, 95% confidence interval [CI], 0.43-0.81; P = .001), and patients transfused at thresholds above 9 g/dL were less likely to survive their ICU stay than those not transfused. Patients of the acute blood loss group who were transfused appeared to benefit or were not harmed by transfusion. CONCLUSION: Conservative RBC product transfusion practices for groups that are targeted by guidelines are justified by outcomes observed in clinical practice. This study provides evidence for the liberal administration of RBC products to critically ill adults with acute blood loss based on association with lower risk of mortality.