Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 20 de 25.963
Filter
1.
Am J Hum Genet ; 109(7): 1190-1198, 2022 Jul 07.
Article in English | MEDLINE | ID: mdl-35803232

ABSTRACT

Digital health solutions, with apps, virtual care, and electronic medical records, are gaining momentum across all medical disciplines, and their adoption has been accelerated, in part, by the COVID-19 pandemic. Personal wearables, sensors, and mobile technologies are increasingly being used to identify health risks and assist in diagnosis, treatment, and monitoring of health and disease. Genomics is a vanguard of digital healthcare as we witness a convergence of the fields of genomic and digital medicine. Spurred by the acute need to increase health literacy, empower patients' preference-sensitive decisions, or integrate vast amounts of complex genomic data into the clinical workflow, there has been an emergence of digital support tools in genomics-enabled care. We present three use cases that demonstrate the application of these converging technologies: digital genomics decision support tools, conversational chatbots to scale the genetic counseling process, and the digital delivery of comprehensive genetic services. These digital solutions are important to facilitate patient-centered care delivery, improve patient outcomes, and increase healthcare efficiencies in genomic medicine. Yet the development of these innovative digital genomic technologies also reveals strategic challenges that need to be addressed before genomic digital health can be broadly adopted. Alongside key evidentiary gaps in clinical and cost-effectiveness, there is a paucity of clinical guidelines, policy, and regulatory frameworks that incorporate digital health. We propose a research agenda, guided by learning healthcare systems, to realize the vision of digital health-enabled genomics to ensure its sustainable and equitable deployment in clinical care.


Subject(s)
COVID-19 , Pandemics , COVID-19/genetics , Delivery of Health Care , Electronic Health Records , Genomics , Humans
2.
BMJ ; 378: e071249, 2022 07 20.
Article in English | MEDLINE | ID: mdl-35858698

ABSTRACT

OBJECTIVE: To estimate waning of covid-19 vaccine effectiveness over six months after second dose. DESIGN: Cohort study, approved by NHS England. SETTING: Linked primary care, hospital, and covid-19 records within the OpenSAFELY-TPP database. PARTICIPANTS: Adults without previous SARS-CoV-2 infection were eligible, excluding care home residents and healthcare professionals. EXPOSURES: People who had received two doses of BNT162b2 or ChAdOx1 (administered during the national vaccine rollout) were compared with unvaccinated people during six consecutive comparison periods, each of four weeks. MAIN OUTCOME MEASURES: Adjusted hazard ratios for covid-19 related hospital admission, covid-19 related death, positive SARS-CoV-2 test, and non-covid-19 related death comparing vaccinated with unvaccinated people. Waning vaccine effectiveness was quantified as ratios of adjusted hazard ratios per four week period, separately for subgroups aged ≥65 years, 18-64 years and clinically vulnerable, 40-64 years, and 18-39 years. RESULTS: 1 951 866 and 3 219 349 eligible adults received two doses of BNT162b2 and ChAdOx1, respectively, and 2 422 980 remained unvaccinated. Waning of vaccine effectiveness was estimated to be similar across outcomes and vaccine brands. In the ≥65 years subgroup, ratios of adjusted hazard ratios for covid-19 related hospital admission, covid-19 related death, and positive SARS-CoV-2 test ranged from 1.19 (95% confidence interval 1.14 to 1.24)to 1.34 (1.09 to 1.64) per four weeks. Despite waning vaccine effectiveness, rates of covid-19 related hospital admission and death were substantially lower among vaccinated than unvaccinated adults up to 26 weeks after the second dose, with estimated vaccine effectiveness ≥80% for BNT162b2, and ≥75% for ChAdOx1. By weeks 23-26, rates of positive SARS-CoV-2 test in vaccinated people were similar to or higher than in unvaccinated people (adjusted hazard ratios up to 1.72 (1.11 to 2.68) for BNT162b2 and 1.86 (1.79 to 1.93) for ChAdOx1). CONCLUSIONS: The rate at which estimated vaccine effectiveness waned was consistent for covid-19 related hospital admission, covid-19 related death, and positive SARS-CoV-2 test and was similar across subgroups defined by age and clinical vulnerability. If sustained to outcomes of infection with the omicron variant and to booster vaccination, these findings will facilitate scheduling of booster vaccination.


Subject(s)
COVID-19 , SARS-CoV-2 , Adult , BNT162 Vaccine , COVID-19/epidemiology , COVID-19/prevention & control , COVID-19 Vaccines , ChAdOx1 nCoV-19 , Cohort Studies , Electronic Health Records , Humans
3.
Sci Rep ; 12(1): 11347, 2022 Jul 05.
Article in English | MEDLINE | ID: mdl-35790802

ABSTRACT

Postoperative patients are at risk of life-threatening complications such as hemodynamic decompensation or arrhythmia. Automated detection of patients with such risks via a real-time clinical decision support system may provide opportunities for early and timely interventions that can significantly improve patient outcomes. We utilize multimodal features derived from digital signal processing techniques and tensor formation, as well as the electronic health record (EHR), to create machine learning models that predict the occurrence of several life-threatening complications up to 4 hours prior to the event. In order to ensure that our models are generalizable across different surgical cohorts, we trained the models on a cardiac surgery cohort and tested them on vascular and non-cardiac acute surgery cohorts. The best performing models achieved an area under the receiver operating characteristic curve (AUROC) of 0.94 on training and 0.94 and 0.82, respectively, on testing for the 0.5-hour interval. The AUROCs only slightly dropped to 0.93, 0.92, and 0.77, respectively, for the 4-hour interval. This study serves as a proof-of-concept that EHR data and physiologic waveform data can be combined to enable the early detection of postoperative deterioration events.


Subject(s)
Decision Support Systems, Clinical , Machine Learning , Electronic Health Records , Humans , Postoperative Period , ROC Curve
4.
Sci Rep ; 12(1): 11734, 2022 Jul 11.
Article in English | MEDLINE | ID: mdl-35817885

ABSTRACT

The Electronic Medical Record (EMR) provides an opportunity to manage patient care efficiently and accurately. This includes clinical decision support tools for the timely identification of adverse events or acute illnesses preceded by deterioration. This paper presents a machine learning-driven tool developed using real-time EMR data for identifying patients at high risk of reaching critical conditions that may demand immediate interventions. This tool provides a pre-emptive solution that can help busy clinicians to prioritize their efforts while evaluating the individual patient risk of deterioration. The tool also provides visualized explanation of the main contributing factors to its decisions, which can guide the choice of intervention. When applied to a test cohort of 18,648 patient records, the tool achieved 100% sensitivity for prediction windows 2-8 h in advance for patients that were identified at 95%, 85% and 70% risk of deterioration.


Subject(s)
Electronic Health Records , Machine Learning , Cohort Studies , Humans
5.
BMC Neurol ; 22(1): 256, 2022 Jul 12.
Article in English | MEDLINE | ID: mdl-35820867

ABSTRACT

BACKGROUND: Risk-stratification tools that have been developed to identify transient ischemic attack (TIA) patients at risk of recurrent vascular events typically include factors which are not readily available in electronic health record systems. Our objective was to evaluate two TIA risk stratification approaches using electronic health record data. METHODS: Patients with TIA who were cared for in Department of Veterans Affairs hospitals (October 2015-September 2018) were included. The six outcomes were mortality, recurrent ischemic stroke, and the combined endpoint of stroke or death at 90-days and 1-year post-index TIA event. The cohort was split into development and validation samples. We examined the risk stratification of two scores constructed using electronic health record data. The Clinical Assessment Needs (CAN) score is a validated measure of risk of hospitalization or death. The PREVENT score was developed specifically for TIA risk stratification. RESULTS: A total of N = 5250 TIA patients were included in the derivation sample and N = 4248 in the validation sample. The PREVENT score had higher c-statistics than the CAN score across all outcomes in both samples. Within the validation sample the c-statistics for the PREVENT score were: 0.847 for 90-day mortality, 0.814 for 1-year mortality, 0.665 for 90-day stroke, and 0.653 for 1-year stroke, 0.699 for 90-day stroke or death, and 0.744 for 1-year stroke or death. The PREVENT score classified patients into categories with extreme nadir and zenith outcome rates. The observed 1-year mortality rate among validation patients was 7.1%; the PREVENT score lowest decile of patients had 0% mortality and the highest decile group had 30.4% mortality. CONCLUSIONS: The PREVENT score had strong c-statistics for the mortality outcomes and classified patients into distinct risk categories. Learning healthcare systems could implement TIA risk stratification tools within electronic health records to support ongoing quality improvement. REGISTRATION: ClinicalTrials.gov Identifier: NCT02769338 .


Subject(s)
Ischemic Attack, Transient , Stroke , Cohort Studies , Electronic Health Records , Hospitalization , Humans , Ischemic Attack, Transient/diagnosis , Ischemic Attack, Transient/epidemiology , Stroke/diagnosis , Stroke/epidemiology
6.
Appl Clin Inform ; 13(3): 681-691, 2022 May.
Article in English | MEDLINE | ID: mdl-35830863

ABSTRACT

BACKGROUND: Automated electronic result notifications can alert health care providers of important clinical results. In contrast to historical notification systems, which were predominantly focused on critical laboratory abnormalities and often not very customizable, modern electronic health records provide capabilities for subscription-based electronic notification. This capability has not been well studied. OBJECTIVES: The purpose of this study was to develop an understanding of when and how a provider decides to use a subscription-based electronic notification. Better appreciation for the factors that contribute to selecting such notifications could aid in improving the functionality of these tools. METHODS: We performed an 8-month quantitative assessment of 3,291 notifications and a qualitative survey assessment of 73 providers who utilized an elective notification tool in our electronic health record. RESULTS: We found that most notifications were requested by attending physicians (∼60%) and from internal medicine specialty (∼25%). Most providers requested only a few notifications while a small minority (nearly 5%) requested 10 or more in the study period. The majority (nearly 30%) of requests were for chemistry laboratories. Survey respondents reported using the tool predominantly for important or time-sensitive laboratories. Overall opinions of the tool were positive (median = 7 out of 10, 95% confidence interval: 6-9), with 40% of eligible respondents reporting the tool improved quality of care. Reported examples included time to result review, monitoring of heparin drips, and reviewing pathology results. CONCLUSION: Developing an understanding for when and how providers decide to be notified of clinical results can help aid in the design and improvement of clinical tools, such as improved elective notifications. These tools may lead to reduced time to result review which could in turn improve clinical care quality.


Subject(s)
Electronic Health Records , Motivation , Demography , Electronics , Health Personnel , Humans
7.
Sci Rep ; 12(1): 11976, 2022 Jul 13.
Article in English | MEDLINE | ID: mdl-35831356

ABSTRACT

Borderline personality disorder (BoPD or BPD) is highly prevalent and characterized by reactive moods, impulsivity, behavioral dysregulation, and distorted self-image. Yet the BoPD diagnosis is underutilized and patients with BoPD are frequently misdiagnosed resulting in lost opportunities for appropriate treatment. Automated screening of electronic health records (EHRs) is one potential strategy to help identify possible BoPD patients who are otherwise undiagnosed. We present the development and analytical validation of a BoPD screening algorithm based on routinely collected and structured EHRs. This algorithm integrates rule-based selection and machine learning (ML) in a two-step framework by first selecting potential patients based on the presence of comorbidities and characteristics commonly associated with BoPD, and then predicting whether the patients most likely have BoPD. Leveraging a large-scale US-based de-identified EHR database and our clinical expert's rating of two random samples of patient EHRs, results show that our screening algorithm has a high consistency with our clinical expert's ratings, with area under the receiver operating characteristic (AUROC) 0.837 [95% confidence interval (CI) 0.778-0.892], positive predictive value 0.717 (95% CI 0.583-0.836), accuracy 0.820 (95% CI 0.768-0.873), sensitivity 0.541 (95% CI 0.417-0.667) and specificity 0.922 (95% CI 0.880-0.960). Our aim is, to provide an additional resource to facilitate clinical decision making and promote the development of digital medicine.


Subject(s)
Borderline Personality Disorder , Electronic Health Records , Algorithms , Borderline Personality Disorder/diagnosis , Borderline Personality Disorder/epidemiology , Databases, Factual , Humans , Machine Learning
8.
Health Informatics J ; 28(3): 14604582221113439, 2022.
Article in English | MEDLINE | ID: mdl-35852472

ABSTRACT

This study synthesized the available evidence of simulation-based electronic health records (EHRs) training in educational and clinical environments for healthcare providers in the literature. The Arksey and O'Malley methodological framework was employed. A systematic search was carried out in relevant databases from inception to January 2020, identifying 24 studies for inclusion. Three themes emerged: (a) role of simulation-based EHR training in evaluating improvement interventions, (b) debriefing and feedback methods used, and (c) challenges of evaluating simulation-based EHR training. The majority of the studies aimed to emphasize the practical skills of individual medical trainees and employed post-simulation feedback as the feedback method. Future research should focus on (a) using simulation-based EHR training to achieve specific learning goals, (b) investigating aspects of clinical performance that are susceptible to skill decay, and (c) examining the influence of simulation-based EHR training on team dynamics.


Subject(s)
Electronic Health Records , Simulation Training , Feedback , Health Personnel/education , Humans , Learning
9.
PLoS One ; 17(7): e0269867, 2022.
Article in English | MEDLINE | ID: mdl-35802569

ABSTRACT

BACKGROUND: Atrial fibrillation (AF) burden on patients and healthcare systems warrants innovative strategies for screening asymptomatic individuals. OBJECTIVE: We sought to externally validate a predictive model originally developed in a German population to detect unidentified incident AF utilising real-world primary healthcare databases from countries in Europe and Australia. METHODS: This retrospective cohort study used anonymized, longitudinal patient data from 5 country-level primary care databases, including Australia, Belgium, France, Germany, and the UK. The study eligibility included adult patients (≥45 years) with either an AF diagnosis (cases) or no diagnosis (controls) who had continuous enrolment in the respective database prior to the study period. Logistic regression was fitted to a binary response (yes/no) for AF diagnosis using pre-determined risk factors. RESULTS: AF patients were from Germany (n = 63,562), the UK (n = 42,652), France (n = 7,213), Australia (n = 2,753), and Belgium (n = 1,371). Cases were more likely to have hypertension or other cardiac conditions than controls in all validation datasets compared to the model development data. The area under the receiver operating characteristic (ROC) curve in the validation datasets ranged from 0.79 (Belgium) to 0.84 (Germany), comparable to the German study model, which had an area under the curve of 0.83. Most validation sets reported similar specificity at approximately 80% sensitivity, ranging from 67% (France) to 71% (United Kingdom). The positive predictive value (PPV) ranged from 2% (Belgium) to 16% (Germany), and the number needed to be screened was 50 in Belgium and 6 in Germany. The prevalence of AF varied widely between these datasets, which may be related to different coding practices. Low prevalence affected PPV, but not sensitivity, specificity, and ROC curves. CONCLUSIONS: AF risk prediction algorithms offer targeted ways to identify patients using electronic health records, which could improve screening number and the cost-effectiveness of AF screening if implemented in clinical practice.


Subject(s)
Atrial Fibrillation , Adult , Atrial Fibrillation/diagnosis , Atrial Fibrillation/epidemiology , Electronic Health Records , Humans , Predictive Value of Tests , Retrospective Studies , United Kingdom/epidemiology
10.
PLoS One ; 17(7): e0270220, 2022.
Article in English | MEDLINE | ID: mdl-35816481

ABSTRACT

The prevalence of patients who are Incapacitated with No Evident Advance Directives or Surrogates (INEADS) remains unknown because such data are not routinely captured in structured electronic health records. This study sought to develop and validate a natural language processing (NLP) algorithm to identify information related to being INEADS from clinical notes. We used a publicly available dataset of critical care patients from 2001 through 2012 at a United States academic medical center, which contained 418,393 relevant clinical notes for 23,904 adult admissions. We developed 17 subcategories indicating reduced or elevated potential for being INEADS, and created a vocabulary of terms and expressions within each. We used an NLP application to create a language model and expand these vocabularies. The NLP algorithm was validated against gold standard manual review of 300 notes and showed good performance overall (F-score = 0.83). More than 80% of admissions had notes containing information in at least one subcategory. Thirty percent (n = 7,134) contained at least one of five social subcategories indicating elevated potential for being INEADS, and <1% (n = 81) contained at least four, which we classified as high likelihood of being INEADS. Among these, n = 8 admissions had no subcategory indicating reduced likelihood of being INEADS, and appeared to meet the definition of INEADS following manual review. Among the remaining n = 73 who had at least one subcategory indicating reduced likelihood of being INEADS, manual review of a 10% sample showed that most did not appear to be INEADS. Compared with the full cohort, the high likelihood group was significantly more likely to die during hospitalization and within four years, to have Medicaid, to have an emergency admission, and to be male. This investigation demonstrates potential for NLP to identify INEADS patients, and may inform interventions to enhance advance care planning for patients who lack social support.


Subject(s)
Electronic Health Records , Natural Language Processing , Adult , Advance Directives , Algorithms , Critical Care , Decision Making , Humans , Male
11.
Ann Fam Med ; 20(4): 312-318, 2022.
Article in English | MEDLINE | ID: mdl-35879072

ABSTRACT

PURPOSE: Use of the electronic health record (EHR) during face-to-face clinical encounters affects communication, and prior research has been inconclusive regarding its effect. This survey study assessed health care practitioner use of EHR-specific communication skills and patient and practitioner experiences and attitudes regarding EHR use during clinical encounters. METHODS: For this US-based study, we distributed previously validated surveys to practitioners and adult patients (aged >18 years) at academic primary care practices from July 1, 2018 through August 31, 2018. The electronic practitioner survey was completed first; a paper survey was administered to patients after appointments. Descriptive statistics were calculated, and the Cochran-Armitage test was used to assess for associations between key variables. RESULTS: The practitioner response was 72.9% (43/59); patient response, 45.2% (452/1,000). Practitioners reported maintaining less eye contact (79.1%), listening less carefully (53.5%), focusing less on patients (65.1%), and visits feeling less personal (62.8%). However, patients reported that practitioners provided sufficient eye contact (96.8%) and listened carefully (97.0%); they disagreed that practitioners focused less on them (86.7%) or that visits felt less personal (87.2%). Patients thought EHR use was positive (91.7%); only one-third of practitioners (37.2%) thought that patients would agree with that statement. Practitioners reported stress, burnout, and a lack of sufficient time for EHR documentation. CONCLUSIONS: A discrepancy existed in this study between patient and practitioner experiences and attitudes about EHR use, which appeared to negatively affect the experience of health care practitioners but not patients. Organizations should adopt formal strategies to improve practitioner experiences with EHR use.


Subject(s)
Burnout, Professional , Electronic Health Records , Adult , Communication , Documentation , Humans , Surveys and Questionnaires
13.
Ann Fam Med ; 20(4): 358-361, 2022.
Article in English | MEDLINE | ID: mdl-35879074

ABSTRACT

The World Organization of Family Doctors (WONCA) developed the third edition of the International Classification of Primary Care (ICPC-3) to support the shift from a medical perspective to a person-centered perspective in primary health care. The previous editions (ICPC-1 and ICPC-2) allowed description of 3 important elements of health care encounters: the reason for the encounter, the diagnosis and/or health problem, and the process of care. The ICPC-3 adds function-related information as a fourth element, thereby capturing most parts of the encounter in a single practical and concise classification. ICPC-3 thus has the potential to give more insight on patients' activities and functioning, supporting physicians in shifting from a strict medical/disease-based approach to care to a more person-centered approach. The ICPC-3 is also expanded with a new chapter for visits pertaining to immunizations and for coding of special screening examinations and public health promotion; in addition, it contains classes for programs related to reported conditions (eg, a cardiovascular program, a heart failure program) and can accommodate relevant national or regional classes. Classes are selected based on what is truly and frequently occurring in daily practice. Each class has its own codes. Less frequently used concepts pertaining to morbidity are captured as inclusions within the main classes. Implementation of the ICPC-3 in an electronic health record allows provision of meaningful feedback to primary care, and supports the exchange of information within teams and between primary and secondary care. It also gives policy makers and funders insight into what is happening in primary care and thus has the potential to improve provision of care.


Subject(s)
Electronic Health Records , Primary Health Care , Delivery of Health Care , Humans , Physicians, Family
14.
Ann Fam Med ; 20(4): 348-352, 2022.
Article in English | MEDLINE | ID: mdl-35879076

ABSTRACT

Card studies-short surveys about the circumstances within which patients receive care-are traditionally completed on physical cards. We report on the development of an electronic health record (EHR)-embedded card study intended to decrease logistical challenges inherent to paper-based approaches, including distributing, tracking, and transferring the physical cards, as well as data entry and respondent prompts, while simultaneously decreasing the complexity for participants and facilitating rich analyses by linking to clinical and demographic data found in the EHR. Developing the EHR-based programming and data extraction was time consuming, required specialized expertise, and necessitated iteration to rectify issues encountered during implementation. Nonetheless, future EHR-embedded card studies will be able to replicate many of the same processes as informed by these results. Once built, the EHR-embedded card study simplified survey implementation for both the research team and clinic staff, resulting in research-quality data, the ability to link survey responses to relevant EHR data, and a 79% response rate. This detailed accounting of the development and implementation process, including issues encountered and addressed, might guide others in conducting EHR-embedded card studies.


Subject(s)
Electronic Health Records , Primary Health Care , Humans , Surveys and Questionnaires
15.
Ann Fam Med ; 20(20 Suppl 1)2022 04 01.
Article in English | MEDLINE | ID: mdl-35881493

ABSTRACT

Context: Most epidemiological research on eczema has largely relied on patient survey data. With the increasing use of electronic medical records (EMR) in primary care, there has been a shift in epidemiological research towards the use of validated case definitions to study disease. Objective: Apply a validated case definition for eczema to EMR data from primary care providers participating in the Canadian Primary Care Sentential Surveillance Network (CPCSSN) to determine the prevalence of diagnosed eczema in Canada and describe patient's characteristics including risk factors and comorbidities. Study Design: Cross-sectional study. Dataset: EMR data from 1,574 primary care providers in seven Canadian provinces. Population Studied: Patient records were examined for those with at least one encounter with a family physician, nurse practitioner or community pediatrician participating in CPCSSN between January 1, 2017, and December 31, 2019 (N= 689,301 patients). Outcome Measures: Primary outcome was lifetime prevalence of eczema. Secondary outcomes were demographics of eczema patients and the association between eczema and various comorbidities. Results: Descriptive statistics revealed a lifetime prevalence of documented eczema of 11.6% overall, 15.1% in those <19 years, and 11.5% in those >19 years. Patients with eczema were more likely to be smokers. Using the Material and Social Deprivation Index we found eczema was more prevalent among the least materially and socially deprived quintiles. In logistic regression, female patients (OR, 1.29; 95% CI, 1.27-1.32) and patients <19 years (OR, 1.27; 95% CI, 1.19-1.35) had higher odds of eczema compared to male patients and patients aged >19 years. Patients with comorbidities such as rhinitis (OR, 2.11; 95% CI, 2.06-2.17), asthma (OR, 1.4; 95% CI, 1.37-1.43), any allergy (OR, 1.09, 95% CI 1.06-1.11), COPD (OR, 1.1; 95% CI, 1.06-1.14) and anxiety (OR, 1.66; 95% CI, 1.63-1.69) had higher odds of eczema compared to patients without these comorbidities. Depression (OR, 0.96; 95% CI, 0.94-0.98) and obesity (OR, 0.96; 95% CI, 0.94-0.98) were negatively associated with a diagnosis of eczema. Conclusion: This is the first study in Canada to determine the prevalence of primary care provider documented eczema using EMR data. This study can inform and improve disease surveillance as well as future studies exploring burden of illness, trends or interventions related to eczema care in Canada.


Subject(s)
Eczema , Electronic Health Records , Canada/epidemiology , Cross-Sectional Studies , Eczema/epidemiology , Female , Humans , Male , Prevalence , Primary Health Care
16.
J Am Heart Assoc ; 11(15): e026014, 2022 Aug 02.
Article in English | MEDLINE | ID: mdl-35904194

ABSTRACT

Background Models predicting atrial fibrillation (AF) risk, such as Cohorts for Heart and Aging Research in Genomic Epidemiology AF (CHARGE-AF), have not performed as well in electronic health records. Natural language processing (NLP) may improve models by using narrative electronic health record text. Methods and Results From a primary care network, we included patients aged ≥65 years with visits between 2003 and 2013 in development (n=32 960) and internal validation cohorts (n=13 992). An external validation cohort from a separate network from 2015 to 2020 included 39 051 patients. Model features were defined using electronic health record codified data and narrative data with NLP. We developed 2 models to predict 5-year AF incidence using (1) codified+NLP data and (2) codified data only and evaluated model performance. The analysis included 2839 incident AF cases in the development cohort and 1057 and 2226 cases in internal and external validation cohorts, respectively. The C-statistic was greater (P<0.001) in codified+NLP model (0.744 [95% CI, 0.735-0.753]) compared with codified-only (0.730 [95% CI, 0.720-0.739]) in the development cohort. In internal validation, the C-statistic of codified+NLP was modestly higher (0.735 [95% CI, 0.720-0.749]) compared with codified-only (0.729 [95% CI, 0.715-0.744]; P=0.06) and CHARGE-AF (0.717 [95% CI, 0.703-0.731]; P=0.002). Codified+NLP and codified-only were well calibrated, whereas CHARGE-AF underestimated AF risk. In external validation, the C-statistic of codified+NLP (0.750 [95% CI, 0.740-0.760]) remained higher (P<0.001) than codified-only (0.738 [95% CI, 0.727-0.748]) and CHARGE-AF (0.735 [95% CI, 0.725-0.746]). Conclusions Estimation of 5-year risk of AF can be modestly improved using NLP to incorporate narrative electronic health record data.


Subject(s)
Atrial Fibrillation , Natural Language Processing , Atrial Fibrillation/diagnosis , Atrial Fibrillation/epidemiology , Cohort Studies , Electronic Health Records , Humans , Incidence , Risk Assessment/methods
17.
Ann Fam Med ; 20(20 Suppl 1)2022 04 01.
Article in English | MEDLINE | ID: mdl-35904800

ABSTRACT

Context: Posttraumatic stress disorder (PTSD) is a chronic mental health disorder associated with significant morbidity and economic cost. Primary care providers are frequently involved in the ongoing management of patients experiencing PTSD, as well as related comorbid conditions. Despite recognized need to enhance PTSD management in primary care settings, knowledge regarding its prevalence in these settings is limited. Objective: To apply a validated case definition of PTSD to electronic medical records (EMRs) of family physicians and nurse practitioners participating in the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Study Design: Retrospective cross-sectional study. Dataset: This study accessed de-identified EMR from 1,574 primary care providers participating in the CPCSSN. Population Studied: The study population included all patients with at least one visit to a primary care provider participating in the CPCSSN between January 1, 2017 and December 31, 2019 (N = 689,301). Outcome Measures: We identified patients with PTSD and described associations between PTSD and patient characteristics (including sex, age, geography, depression, anxiety, medical comorbidities, substance use and social and material deprivation) using multivariable logistic regression models. Results: Among the 689,301 patients meeting inclusion criteria, 8,213 (1.2%) had a diagnosis of PTSD. Patients with PTSD were significantly more likely to reside in an urban location (84.9% vs. 80.4%; p-value <.0001) and have one or more comorbid conditions (90.8% vs. 70.2%; p-value <.0001). On multivariable logistic regression analysis, patients with depression (OR 4.8; 95%CI 4.6-5.1) and anxiety (OR 2.2; 95%CI 2.1-2.3) had increased odds of having PTSD compared to patients without depression or anxiety. Patients with alcohol (OR 1.8; 95%CI 1.6-1.9) and drug (OR 3.1; 95%CI 2.9-3.3) use disorders had significantly higher odds of PTSD compared to patients without these disorders. Patients in the most deprived neighborhoods based on census data had 4.2 times higher odds of have PTSD (95%CI 3.2-5.43) compared to patients in the least deprived areas. Conclusions: This is the first study to describe PTSD prevalence in a large Canadian sample of primary care patients using an EMR-based case definition. Characterizing patients with PTSD in primary care may improve disease surveillance and inform the interdisciplinary care required to manage PTSD symptoms.


Subject(s)
Stress Disorders, Post-Traumatic , Canada/epidemiology , Chronic Disease , Cross-Sectional Studies , Electronic Health Records , Humans , Primary Health Care , Retrospective Studies , Stress Disorders, Post-Traumatic/epidemiology , Stress Disorders, Post-Traumatic/psychology
18.
Medicine (Baltimore) ; 101(30): e29627, 2022 Jul 29.
Article in English | MEDLINE | ID: mdl-35905245

ABSTRACT

The Teleprimary Care-Oral Health Clinical Information System (TPC-OHCIS) is an updated electronic medical record (EMR) that has been applied in Malaysian primary healthcare. Recognizing the level of patient satisfaction following EMR implementation is crucial for assessing the performance of health care services. Hence, the main objective of this study was to compare the level of patient satisfaction between EMR-based clinics and paper-based clinics. The study was a quasi-experimental design that used a control group and was conducted among patients in 14 public primary healthcare facilities in the Seremban district of Malaysia from May 10, to June 30, 2021. Patient satisfaction was assessed using the validated Short-Form Patient Satisfaction Questionnaire, which consisted of 7 subscales. All data were analyzed using the IBM Statistical Package for Social Sciences version 21. A total of 321 patients consented to participate in this study, and 48.9% of them were from EMR clinics. The mean score for the communication subscale was the highest at 4.08 and 3.96 at EMR-adopted clinics and paper-based record clinics. There were significant differences in general satisfaction and communication subscales, with higher patient satisfaction found in clinics using EMR. With the utilization of EMR, patient satisfaction and communication in delivering healthcare services have improved.


Subject(s)
Electronic Health Records , Quality of Health Care , Health Services , Humans , Patient Satisfaction , Surveys and Questionnaires
19.
BMC Med Inform Decis Mak ; 22(1): 201, 2022 Jul 30.
Article in English | MEDLINE | ID: mdl-35908055

ABSTRACT

OBJECTIVE: Named entity recognition (NER) is a key and fundamental part of many medical and clinical tasks, including the establishment of a medical knowledge graph, decision-making support, and question answering systems. When extracting entities from electronic health records (EHRs), NER models mostly apply long short-term memory (LSTM) and have surprising performance in clinical NER. However, increasing the depth of the network is often required by these LSTM-based models to capture long-distance dependencies. Therefore, these LSTM-based models that have achieved high accuracy generally require long training times and extensive training data, which has obstructed the adoption of LSTM-based models in clinical scenarios with limited training time. METHOD: Inspired by Transformer, we combine Transformer with Soft Term Position Lattice to form soft lattice structure Transformer, which models long-distance dependencies similarly to LSTM. Our model consists of four components: the WordPiece module, the BERT module, the soft lattice structure Transformer module, and the CRF module. RESULT: Our experiments demonstrated that this approach increased the F1 by 1-5% in the CCKS NER task compared to other models based on LSTM with CRF and consumed less training time. Additional evaluations showed that lattice structure transformer shows good performance for recognizing long medical terms, abbreviations, and numbers. The proposed model achieve 91.6% f-measure in recognizing long medical terms and 90.36% f-measure in abbreviations, and numbers. CONCLUSIONS: By using soft lattice structure Transformer, the method proposed in this paper captured Chinese words to lattice information, making our model suitable for Chinese clinical medical records. Transformers with Mutilayer soft lattice Chinese word construction can capture potential interactions between Chinese characters and words.


Subject(s)
Electronic Health Records , Natural Language Processing , China , Humans
20.
Neural Netw ; 153: 339-348, 2022 Sep.
Article in English | MEDLINE | ID: mdl-35779443

ABSTRACT

Hospitals and General Practitioner (GP) surgeries within National Health Services (NHS), collect patient information on a routine basis to create personal health records such as family medical history, chronic diseases, medications and dosing. The collected information could be used to build and model various machine learning algorithms, to simplify the task of those working within the NHS. However, such Electronic Health Records are not made publicly available due to privacy concerns. In our paper, we propose a privacy-preserving Generative Adversarial Network (pGAN), which can generate synthetic data of high quality, while preserving the privacy and statistical properties of the source data. pGAN is evaluated on two distinct datasets, one posing as a Classification task, and the other as a Regression task. Privacy score of generated data is calculated using the Nearest Neighbour Adversarial Accuracy. Cosine similarity scores of synthetic data from our proposed model indicate that the data generated is similar in nature, but not identical. Additionally, our proposed model was able to preserve privacy while maintaining high utility. Machine learning models trained on both synthetic data and original data have achieved accuracies of 74.3% and 74.5% respectively on the classification dataset; while they have attained an R2-Score of 0.84 and 0.85 on synthetic and original data of the regression task respectively. Our results, therefore, indicate that synthetic data from the proposed model could replace the use of original data for machine learning while preserving privacy.


Subject(s)
Electronic Health Records , Privacy , Algorithms , Data Collection , Humans , Machine Learning
SELECTION OF CITATIONS
SEARCH DETAIL
...