Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 503
Filter
1.
JMIR Public Health Surveill ; 7(3): e26719, 2021 03 24.
Article in English | MEDLINE | ID: covidwho-2197901

ABSTRACT

BACKGROUND: Patient travel history can be crucial in evaluating evolving infectious disease events. Such information can be challenging to acquire in electronic health records, as it is often available only in unstructured text. OBJECTIVE: This study aims to assess the feasibility of annotating and automatically extracting travel history mentions from unstructured clinical documents in the Department of Veterans Affairs across disparate health care facilities and among millions of patients. Information about travel exposure augments existing surveillance applications for increased preparedness in responding quickly to public health threats. METHODS: Clinical documents related to arboviral disease were annotated following selection using a semiautomated bootstrapping process. Using annotated instances as training data, models were developed to extract from unstructured clinical text any mention of affirmed travel locations outside of the continental United States. Automated text processing models were evaluated, involving machine learning and neural language models for extraction accuracy. RESULTS: Among 4584 annotated instances, 2659 (58%) contained an affirmed mention of travel history, while 347 (7.6%) were negated. Interannotator agreement resulted in a document-level Cohen kappa of 0.776. Automated text processing accuracy (F1 85.6, 95% CI 82.5-87.9) and computational burden were acceptable such that the system can provide a rapid screen for public health events. CONCLUSIONS: Automated extraction of patient travel history from clinical documents is feasible for enhanced passive surveillance public health systems. Without such a system, it would usually be necessary to manually review charts to identify recent travel or lack of travel, use an electronic health record that enforces travel history documentation, or ignore this potential source of information altogether. The development of this tool was initially motivated by emergent arboviral diseases. More recently, this system was used in the early phases of response to COVID-19 in the United States, although its utility was limited to a relatively brief window due to the rapid domestic spread of the virus. Such systems may aid future efforts to prevent and contain the spread of infectious diseases.


Subject(s)
Communicable Diseases, Emerging/diagnosis , Electronic Health Records , Information Storage and Retrieval/methods , Public Health Surveillance/methods , Travel/statistics & numerical data , Algorithms , COVID-19/epidemiology , Communicable Diseases, Emerging/epidemiology , Feasibility Studies , Female , Humans , Machine Learning , Male , Middle Aged , Natural Language Processing , Reproducibility of Results , United States/epidemiology
3.
BMJ Open Qual ; 11(4)2022 11.
Article in English | MEDLINE | ID: covidwho-2137805

ABSTRACT

BACKGROUND: In response to the severe hepatitis A outbreak that occurred in Michigan between August 2016 and September 2019, our multihospital health system implemented an electronic medical record (EMR)-based vaccination intervention across its nine emergency departments (EDs). The objectives were to explore the impact of this intervention on increasing vaccination rates among high-risk individuals and to assess the barriers to use of a computerised vaccine reminder system. METHODS: All patients who were 18 years or older were screened using an electronic nursing questionnaire. If a patient was at high risk based on the questionnaire, an electronic best practice advisory (BPA) would trigger and give the physician or advanced practice provider the option to order the hepatitis A vaccine. We explored the vaccination rates in the 24-month preintervention and the 18-month intervention periods. We then administered a survey to physicians, advanced practice providers and nurses evaluating their perceptions and barriers to use of the EMR intervention. RESULTS: During the preintervention period, 49 vaccines were ordered (5.5 per 100 000 patient visits) and 32 were administered (3.6 per 100 000 patient visits). During the intervention period, 574 865 patient visits (74.3%) were screened. 2494 vaccines (322 per 100 000 patient visits) were ordered, and 1205 vaccines (155 per 100 000 patients visits) were administered. Physicians and advanced practice providers were initially compliant with the BPA's use, but compliance declined over time. Surveys revealed that the major barrier to use was lack of time. CONCLUSIONS: EMR screening tools and BPAs can be used in the ED as an effective strategy to vaccinate high-risk individuals. This may be translatable to outbreaks of other vaccine-preventable illnesses like influenza, measles or SARS-CoV-2. Providing ongoing education about the public health initiative and giving feedback to physicians, advanced practice providers and nurses about tool compliance are needed to sustain the improvement over time.


Subject(s)
COVID-19 , Hepatitis A , Influenza Vaccines , Humans , Electronic Health Records , Hepatitis A/epidemiology , Hepatitis A/prevention & control , SARS-CoV-2 , Vaccination , Disease Outbreaks/prevention & control , Emergency Service, Hospital
4.
J Healthc Manag ; 67(6): 425-435, 2022.
Article in English | MEDLINE | ID: covidwho-2135684

ABSTRACT

GOAL: Administrative burden is one of many potential root causes of physician burnout. Scribe documentation assistance can reduce this burden. However, traditional in-person scribe services are challenged by consistent staffing because the model requires the physical presence of a scribe and limits the team to a single individual. In addition, in-person scribes cannot provide the flexible support required for virtual care encounters, which can now pivot geographically and temporally. To respond to these challenges, our health network implemented an asynchronous virtual scribe model and evaluated the program's impact on clinician perceptions of burnout across multiple outpatient specialties. METHODS: Using a mixed-methods, pre-/postdesign, this evaluation measured the impact of an asynchronous virtual scribe program on physician burnout. Physicians were given the Professional Fulfillment Index tool (to self-assess their mental state) and free-text comment surveys before virtual scribe initiation and again at 3-, 6-, and 12-month intervals after program implementation. Descriptive statistics of survey results and qualitative review of free-text entries were analyzed for themes of facilitation and barriers to virtual scribe use. PRINCIPAL FINDINGS: Of 50 physician participants in this study, 42 (84%) completed the preintervention survey and 15 (36%) completed all 4 surveys; 25 participants (50%) discontinued scribe use after 12 months. Burnout levels-as defined by dread, exhaustion, lack of enthusiasm, decrease in empathy, and decrease in colleague connection-all trended toward improvement during this study. Importantly, quality, time savings, burnout, and productivity moved in positive directions as well. PRACTICAL APPLICATION: The cost burden to physicians and the COVID-19 pandemic inhibited the continued use of asynchronous virtual medical scribes. Nevertheless, those who continued in the program have reported positive outcomes, which indicates that the service can be a viable and effective tool to reduce physician burnout.


Subject(s)
Burnout, Professional , COVID-19 , Physicians , Humans , Electronic Health Records , Pandemics , Burnout, Psychological , Burnout, Professional/prevention & control
5.
NPJ Prim Care Respir Med ; 32(1): 49, 2022 Nov 09.
Article in English | MEDLINE | ID: covidwho-2118377

ABSTRACT

Two recruitment strategies for research were compared to prospectively identify patients with breathlessness who are awaiting a diagnosis in primary care. The first method utilised searches of the electronic patient record (EPR), the second method involved an electronic template triggered during a consultation. Using an electronic template triggered at the point of consultation increased recruitment to prospective research approximately nine-fold compared with searching for symptom codes and study mailouts.


Subject(s)
Dyspnea , Referral and Consultation , Humans , Prospective Studies , Dyspnea/diagnosis , Dyspnea/etiology , Electronic Health Records , Primary Health Care
6.
Perspect Health Inf Manag ; 19(4): 1c, 2022.
Article in English | MEDLINE | ID: covidwho-2102053

ABSTRACT

The COVID-19 pandemic led to an increase in cybersecurity attacks on organizations operating in the healthcare industry. Health information professionals and health executives are unable to limit the impact of data breaches on records their organizations handle. While current research focuses on prevention strategies and the understanding of the causes of data breaches, it failed to address how to mitigate the impact of successful cybersecurity attacks. This quantitative research paper examined the effect the healthcare entity type has on the number of impacted individuals for healthcare data breaches that occurred during the pandemic. Health information professionals will be able to mitigate the number of breached records based on their organizational type. Some of this paper's findings include the call for implementation of organizational frameworks aimed to protect patient information, and the call for further research to understand how other factors might affect the impact of healthcare data breaches.


Subject(s)
COVID-19 , Computer Security , Electronic Health Records , Humans , Delivery of Health Care , Pandemics/prevention & control
7.
Int J Environ Res Public Health ; 19(21)2022 Nov 02.
Article in English | MEDLINE | ID: covidwho-2099517

ABSTRACT

The COVID-19 pandemic has caused remarkable psychological overwhelming and an increase in stressors that may trigger suicidal behaviors. However, its impact on the rate of suicidal behaviors has been poorly reported. We conducted a population-based retrospective analysis of all suicidal behaviors attended in healthcare centers of Catalonia (northeast Spain; 7.5 million inhabitants) between January 2017 and June 2022 (secondary use of data routinely reported to central suicide and diagnosis registries). We retrieved data from this period, including an assessment of suicide risk and individuals' socioeconomic as well as clinical characteristics. Data were summarized yearly and for the periods before and after the onset of the COVID-19 pandemic in Spain in March 2020. The analysis included 26,458 episodes of suicidal behavior (21,920 individuals); of these, 16,414 (62.0%) were suicide attempts. The monthly moving average ranged between 300 and 400 episodes until July 2020, and progressively increased to over 600 episodes monthly. In the postpandemic period, suicidal ideation increased at the expense of suicidal attempts. Cases showed a lower suicide risk; the percentage of females and younger individuals increased, whereas the prevalence of classical risk factors, such as living alone, lacking a family network, and a history of psychiatric diagnosis, decreased. In summary, suicidal behaviors have increased during the COVID-19 pandemic, with more episodes of suicidal ideation without attempts in addition to younger and lower risk profiles.


Subject(s)
COVID-19 , Suicidal Ideation , Female , Humans , Incidence , COVID-19/epidemiology , Retrospective Studies , Electronic Health Records , Pandemics , Risk Factors , Prevalence
8.
PLoS One ; 17(10): e0276923, 2022.
Article in English | MEDLINE | ID: covidwho-2098766

ABSTRACT

OBJECTIVE: Identifying the time of SARS-CoV-2 viral infection relative to specific gestational weeks is critical for delineating the role of viral infection timing in adverse pregnancy outcomes. However, this task is difficult when it comes to Electronic Health Records (EHR). In combating the COVID-19 pandemic for maternal health, we sought to develop and validate a clinical information extraction algorithm to detect the time of clinical events relative to gestational weeks. MATERIALS AND METHODS: We used EHR from the National COVID Cohort Collaborative (N3C), in which the EHR are normalized by the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). We performed EHR phenotyping, resulting in 270,897 pregnant women (June 1st, 2018 to May 31st, 2021). We developed a rule-based algorithm and performed a multi-level evaluation to test content validity and clinical validity, and extreme length of gestation (<150 or >300). RESULTS: The algorithm identified 296,194 pregnancies (16,659 COVID-19, 174,744 without COVID-19) in 270,897 pregnant women. For inferring gestational age, 95% cases (n = 40) have moderate-high accuracy (Cohen's Kappa = 0.62); 100% cases (n = 40) have moderate-high granularity of temporal information (Cohen's Kappa = 1). For inferring delivery dates, the accuracy is 100% (Cohen's Kappa = 1). The accuracy of gestational age detection for the extreme length of gestation is 93.3% (Cohen's Kappa = 1). Mothers with COVID-19 showed higher prevalence in obesity or overweight (35.1% vs. 29.5%), diabetes (17.8% vs. 17.0%), chronic obstructive pulmonary disease (0.2% vs. 0.1%), respiratory distress syndrome or acute respiratory failure (1.8% vs. 0.2%). DISCUSSION: We explored the characteristics of pregnant women by different gestational weeks of SARS-CoV-2 infection with our algorithm. TED-PC is the first to infer the exact gestational week linked with every clinical event from EHR and detect the timing of SARS-CoV-2 infection in pregnant women. CONCLUSION: The algorithm shows excellent clinical validity in inferring gestational age and delivery dates, which supports multiple EHR cohorts on N3C studying the impact of COVID-19 on pregnancy.


Subject(s)
COVID-19 , Pregnancy Complications, Infectious , Premature Birth , Female , Pregnancy , Humans , COVID-19/epidemiology , Pandemics , Pregnant Women , Gestational Age , SARS-CoV-2 , Electronic Health Records , Pregnancy Complications, Infectious/diagnosis , Pregnancy Complications, Infectious/epidemiology , Pregnancy Outcome , Algorithms , Premature Birth/epidemiology
10.
Sci Data ; 9(1): 658, 2022 10 27.
Article in English | MEDLINE | ID: covidwho-2087257

ABSTRACT

The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop prediction models and decision support systems to address these challenges. To date, there is no widely accepted clinical prediction benchmark related to the ED based on large-scale public EHRs. An open-source benchmark data platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. Based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we created a benchmark dataset and proposed three clinical prediction benchmarks. This study provides future researchers with insights, suggestions, and protocols for managing data and developing predictive tools for emergency care.


Subject(s)
Benchmarking , COVID-19 , Humans , Electronic Health Records , Pandemics , Emergency Service, Hospital , Machine Learning
11.
WMJ ; 121(3): 189-193, 2022 Oct.
Article in English | MEDLINE | ID: covidwho-2084286

ABSTRACT

BACKGROUND: We describe patient-visit volumes, patient acuity, and demographics in our 4 academic health system emergency departments (ED) before, during, and after implementation of a COVID-19 pandemic safer-at-home order. METHODS: Data were collected from the electronic health record, including patient-visit volumes, chief complaint, Emergency Severity Index (ESI), and patient demographics. Descriptive statistics were performed. RESULTS: There was a 37% decrease in combined ED patient-visit volume during the safer-at-home order period (42% at the academic medical center). ED patient-visit volumes increased after the safer-at-home order concluded. During the safer-at-home order period, there was an increase in the proportion of ESI-2 visits and admission rates from EDs across the system. CONCLUSIONS: Significant differences in ED patient-visit volumes and patient acuity were associated with a safer-at-home order in our academic health system. These differences are similar to experiences of other hospital systems across the country.


Subject(s)
COVID-19 , Humans , COVID-19/epidemiology , Pandemics , Emergency Service, Hospital , Academic Medical Centers , Electronic Health Records , Retrospective Studies
12.
Appl Clin Inform ; 13(5): 949-955, 2022 Oct.
Article in English | MEDLINE | ID: covidwho-2069913

ABSTRACT

BACKGROUND: In response to surges in demand for intensive care unit (ICU) care related to the COVID-19 pandemic, health care systems have had to increase hospital capacity. One institution redeployed certified registered nurse anesthetists (CRNAs) as ICU clinicians, which necessitated training in ICU-specific electronic health record (EHR) workflows prior to redeployment. Under time- and resource-constrained settings, clinical informatics (CI) fellows could effectively be lead instructors for such training. OBJECTIVE: This study aimed to deploy CI fellows as lead EHR instructional trainers for clinician redeployment as part of an organization's response to disaster management. METHODS: CI fellows led a multidisciplinary team alongside subject matter experts to develop and deploy a tailored EHR curriculum comprising in-person classes and online video modules, leveraging high-fidelity simulated patient cases. The participants completed surveys immediately after the in-person training session and after deployment. RESULTS: Eighteen CRNAs participated, with 15 completing the postactivity survey (83%). All felt the training was useful and improved their EHR skills with a Net Promoter score of +87. Most (93%) respondents indicated the pace of the session was "just right," and 100% felt the clarity of instruction was "just right" or "extremely easy" to understand. Twelve participants (67%) completed the postdeployment survey. The training increased comfort in the ICU for all respondents, and 91% felt the training prepared them to work in the ICU with minimal guidance. All stated that the concepts learned would be useful in their anesthesia role. Fifty-eight percent viewed the online video library. CONCLUSION: This case report demonstrates that CI fellows with dual domain expertise in their clinical specialty and informatics are uniquely poised to deliver clinician redeployment EHR training in response to operational crises. Such opportunities can achieve fellowship educational goals while conserving physician resources which can be a strategic option as organizations plan for disaster management.


Subject(s)
COVID-19 , COVID-19/epidemiology , Curriculum , Electronic Health Records , Fellowships and Scholarships , Humans , Pandemics
14.
J Clin Psychiatry ; 82(2)2021 03 03.
Article in English | MEDLINE | ID: covidwho-2066785

ABSTRACT

OBJECTIVE: The early COVID-19 pandemic resulted in great psychosocial disruption and stress, raising speculation that psychiatric disorders may worsen. This study aimed to identify patients vulnerable to worsening mental health during the COVID-19 pandemic. METHODS: This retrospective observational study used electronic health records from March 9 to May 31 in 2019 (n = 94,720) and 2020 (n = 94,589) in a large, community-based health care system. Percent change analysis compared variables standardized to the average patient population for the respective time periods. RESULTS: Compared to 2019, psychiatric visits increased significantly (P < .0001) in 2020, with the majority being telephone/video-based (+264%). Psychiatric care volume increased overall (7%), with the greatest increases in addiction (+42%), behavioral health in primary care (+17%), and adult psychiatry (+5%) clinics. While patients seeking care with preexisting psychiatric diagnoses were mainly stable (−2%), new patients declined (−42%). Visits for substance use (+51%), adjustment (+15%), anxiety (+12%), bipolar (+9%), and psychotic (+6%) disorder diagnoses, and for patients aged 18­25 years (+4%) and 26­39 years (+4%), increased. Child/adolescent and older adult patient visits decreased (−22.7% and −5.5%, respectively), and fewer patients identifying as White (−3.8%) or male (−5.0) or with depression (−3%) or disorders of childhood (−2%) sought care. CONCLUSIONS: The early COVID-19 pandemic was associated with dramatic changes in psychiatric care facilitated by a rapid telehealth care transition. Patient volume, demographic, and diagnostic changes may reflect comfort with telehealth or navigating the psychiatric care system. These data can inform health system resource management and guide future work examining how care delivery changes impact psychiatric care quality and access.


Subject(s)
COVID-19 , Community Health Services/statistics & numerical data , Mental Disorders/epidemiology , Mental Disorders/therapy , Mental Health Services/statistics & numerical data , Patient Acceptance of Health Care/statistics & numerical data , Primary Health Care/statistics & numerical data , Telemedicine/statistics & numerical data , Adolescent , Adult , Child , Electronic Health Records , Female , Humans , Male , Mental Disorders/diagnosis , Middle Aged , Retrospective Studies , Young Adult
17.
Nat Med ; 28(9): 1773-1784, 2022 09.
Article in English | MEDLINE | ID: covidwho-2042327

ABSTRACT

The increasing availability of biomedical data from large biobanks, electronic health records, medical imaging, wearable and ambient biosensors, and the lower cost of genome and microbiome sequencing have set the stage for the development of multimodal artificial intelligence solutions that capture the complexity of human health and disease. In this Review, we outline the key applications enabled, along with the technical and analytical challenges. We explore opportunities in personalized medicine, digital clinical trials, remote monitoring and care, pandemic surveillance, digital twin technology and virtual health assistants. Further, we survey the data, modeling and privacy challenges that must be overcome to realize the full potential of multimodal artificial intelligence in health.


Subject(s)
Artificial Intelligence , Pandemics , Electronic Health Records , Humans , Privacy
18.
Int J Med Inform ; 167: 104863, 2022 11.
Article in English | MEDLINE | ID: covidwho-2041812

ABSTRACT

PURPOSE: To assess, validate and compare the predictive performance of models for in-hospital mortality of COVID-19 patients admitted to the intensive care unit (ICU) over two different waves of infections. Our models were built with high-granular Electronic Health Records (EHR) data versus less-granular registry data. METHODS: Observational study of all COVID-19 patients admitted to 19 Dutch ICUs participating in both the national quality registry National Intensive Care Evaluation (NICE) and the EHR-based Dutch Data Warehouse (hereafter EHR). Multiple models were developed on data from the first 24 h of ICU admissions from February to June 2020 (first COVID-19 wave) and validated on prospective patients admitted to the same ICUs between July and December 2020 (second COVID-19 wave). We assessed model discrimination, calibration, and the degree of relatedness between development and validation population. Coefficients were used to identify relevant risk factors. RESULTS: A total of 1533 patients from the EHR and 1563 from the registry were included. With high granular EHR data, the average AUROC was 0.69 (standard deviation of 0.05) for the internal validation, and the AUROC was 0.75 for the temporal validation. The registry model achieved an average AUROC of 0.76 (standard deviation of 0.05) in the internal validation and 0.77 in the temporal validation. In the EHR data, age, and respiratory-system related variables were the most important risk factors identified. In the NICE registry data, age and chronic respiratory insufficiency were the most important risk factors. CONCLUSION: In our study, prognostic models built on less-granular but readily-available registry data had similar performance to models built on high-granular EHR data and showed similar transportability to a prospective COVID-19 population. Future research is needed to verify whether this finding can be confirmed for upcoming waves.


Subject(s)
COVID-19 , COVID-19/epidemiology , Electronic Health Records , Hospital Mortality , Humans , Intensive Care Units , Netherlands/epidemiology , Registries , Retrospective Studies
19.
Arch Pathol Lab Med ; 146(9): 1053-1055, 2022 09 01.
Article in English | MEDLINE | ID: covidwho-2040319
20.
Euro Surveill ; 27(37)2022 09.
Article in English | MEDLINE | ID: covidwho-2039628

ABSTRACT

We measured vaccine effectiveness (VE) against COVID-19-related severe outcomes in elderly people in Portugal between May and July 2022. In ≥ 80 year-olds, the second booster dose VE was 81% (95% CI: 75-85) and 82% (95% CI: 77-85), respectively, against COVID-19-related hospitalisation and death. The first booster dose VE was 63% (95% CI: 55-70) in ≥ 80 year-olds and 74% (95% CI: 66-80) in 60-79 year-olds against hospitalisation, and 63% (95% CI: 57-69) and 65% (95% CI: 54-74) against death.


Subject(s)
COVID-19 Vaccines , COVID-19 , Aged , COVID-19/prevention & control , Cohort Studies , Electronic Health Records , Hospitalization , Humans , Portugal/epidemiology , Vaccines, Synthetic , mRNA Vaccines
SELECTION OF CITATIONS
SEARCH DETAIL