Additional Value From Free-Text Diagnoses in Electronic Health Records: Hybrid Dictionary and Machine Learning Classification Study.

BACKGROUND: Physicians are hesitant to forgo the opportunity of entering unstructured clinical notes for structured data entry in electronic health records. Does free text increase informational value in comparison with structured data? OBJECTIVE: This study aims to compare information from unstructured text-based chief complaints harvested and processed by a natural language processing (NLP) algorithm with clinician-entered structured diagnoses in terms of their potential utility for automated improvement of patient workflows. METHODS: Electronic health records of 293,298 patient visits at the emergency department of a Swiss university hospital from January 2014 to October 2021 were analyzed. Using emergency department overcrowding as a case in point, we compared supervised NLP-based keyword dictionaries of symptom clusters from unstructured clinical notes and clinician-entered chief complaints from a structured drop-down menu with the following 2 outcomes: hospitalization and high Emergency Severity Index (ESI) score. RESULTS: Of 12 symptom clusters, the NLP cluster was substantial in predicting hospitalization in 11 (92%) clusters; 8 (67%) clusters remained significant even after controlling for the cluster of clinician-determined chief complaints in the model. All 12 NLP symptom clusters were significant in predicting a low ESI score, of which 9 (75%) remained significant when controlling for clinician-determined chief complaints. The correlation between NLP clusters and chief complaints was low (r=-0.04 to 0.6), indicating complementarity of information. CONCLUSIONS: The NLP-derived features and clinicians' knowledge were complementary in explaining patient outcome heterogeneity. They can provide an efficient approach to patient flow management, for example, in an emergency medicine setting. We further demonstrated the feasibility of creating extensive and precise keyword dictionaries with NLP by medical experts without requiring programming knowledge. Using the dictionary, we could classify short and unstructured clinical texts into diagnostic categories defined by the clinician.

Incidence, clinical presentation, management, and outcome of acute pericarditis and myopericarditis.

AIMS: Little is known about the epidemiology, clinical presentation, management, and outcome of acute pericarditis and myopericarditis. METHODS AND RESULTS: The final diagnoses of acute pericarditis, myopericarditis, and non-ST-segment elevation myocardial infarction (NSTEMI) of patients presenting to seven emergency departments in Switzerland with acute chest pain were centrally adjudicated by two independent cardiologists using all information including serial measurements of high-sensitivity cardiac troponin T. The overall incidence of pericarditis and myopericarditis was estimated relative to the established incidence of NSTEMI. Current management and long-term outcome of both conditions were also assessed. Among 2533 chest pain patients, the incidence of pericarditis, myopericarditis, and NSTEMI were 1.9% (n = 48), 1.1% (n = 29), and 21.6% (n = 548), respectively. Accordingly, the estimated incidence of pericarditis and myopericarditis in Switzerland was 10.1 [95% confidence interval (95% CI) 9.3-10.9] and 6.1 (95% CI 5.6-6.7) cases per 100 000 population per year, respectively, vs. 115.0 (95% CI 112.3-117.6) cases per 100 000 population per year for NSTEMI. Pericarditis (85% male, median age 46 years) and myopericarditis (62% male, median age 56 years) had male predominance, and commonly (50% and 97%, respectively) resulted in hospitalization. No patient with pericarditis or myopericarditis died or had life-threatening arrhythmias within 30 days [incidence 0% (95% CI 0.0-4.8%)]. Compared with NSTEMI, the 2-year all-cause mortality adjusted hazard ratio of pericarditis and myopericarditis was 0.40 (95% CI 0.05-2.96), being 0.59 (95% CI 0.40-0.88) for non-cardiac causes of chest pain. CONCLUSION: Pericarditis and myopericarditis are substantially less common than NSTEMI and have an excellent short- and long-term outcome. CLINICAL TRIAL REGISTRATION: ClinicalTrial.gov, number NCT00470587, https://clinicaltrials.gov/ct2/show/NCT00470587.

Machine learning-based CT fractional flow reserve assessment in acute chest pain: first experience.

BACKGROUND: Computed tomography (CT)-derived fractional flow reserve (FFRCT) enables the non-invasive functional assessment of coronary artery stenosis. We evaluated the feasibility and potential clinical role of FFRCT in patients presenting to the emergency department with acute chest pain who underwent chest-pain CT (CPCT). METHODS: For this retrospective IRB-approved study, we included 56 patients (median age: 62 years, 14 females) with acute chest pain who underwent CPCT and who had at least a mild (≥25% diameter) coronary artery stenosis. CPCT was evaluated for the presence of acute plaque rupture and vulnerable plaque features. FFRCT measurements were performed using a machine learning-based software. We assessed the agreement between the results from FFRCT and patient outcome (including results from invasive catheter angiography and from any non-invasive cardiac imaging test, final clinical diagnosis and revascularization) for a follow-up of 3 months. RESULTS: FFRCT was technically feasible in 38/56 patients (68%). Eleven of the 38 patients (29%) showed acute plaque rupture in CPCT; all of them underwent immediate coronary revascularization. Of the remaining 27 patients (71%), 16 patients showed vulnerable plaque features (59%), of whom 11 (69%) were diagnosed with acute coronary syndrome (ACS) and 10 (63%) underwent coronary revascularization. In patients with vulnerable plaque features in CPCT, FFRCT had an agreement with outcome in 12/16 patients (75%). In patients without vulnerable plaque features (n=11), one patient showed myocardial ischemia (9%). In these patients, FFRCT and patient outcome showed an agreement in 10/11 patients (91%). CONCLUSIONS: Our preliminary data show that FFRCT is feasible in patients with acute chest pain who undergo CPCT provided that image quality is sufficient. FFRCT has the potential to improve patient triage by reducing further downstream testing but appears of limited value in patients with CT signs of acute plaque rupture.

Pain management policies and reported practices in Swiss emergency departments: a national survey.

BACKGROUND: Acute pain is the most common complaint of patients presenting to emergency departments (EDs). Effective pain management is a core ED mission, but numerous studies have pointed to insufficient pain treatment or oligoanalgesia. According to a 1997 national survey in Swiss EDs, a validated pain scale was used in only 14%, an analgesia protocol in <5%, and 1.1% had a nurse-initiated pain protocol. Since then, numerous societal and health care factors have led to improved ED pain care. The aim of this study was to assess the state of ED pain management in Switzerland. METHODS: Hospital-based Swiss EDs open 24 hours a day and 7 days a week in 2013 were surveyed using a questionnaire. Data from 2013 were collected. Questions queried the pain management process by nurses and physicians in each ED. RESULTS: The response rate was 115 of 137 eligible EDs (84%). Pain intensity was assessed with a validated instrument in 71% of waiting rooms and in 99% of treatment areas. A nurse-initiated analgesia protocol was available in 56% of waiting rooms and in 70% of treatment areas. Physician pain protocols were available in 75%, and analgesia-sedation protocols in 51%. CONCLUSION: The pain management processes in Swiss EDs have improved over the last 17 years, and are now equivalent to other western countries. Our study did not, however, assess if these improvements resulted in better analgesia at the bedside, an important topic that will require further study.

FIFA Women's World Cup 2011: pre-competition medical assessment of female referees and assistant referees.

BACKGROUND: Precompetition screening was implemented for male referees during the 2010 Fédération Internationale de Football Association (FIFA) Word Cup. In contrast, female football referees have been neglected in this respect although they experience similar physical work loads compared to male referees. METHODS: The standardised football-specific pre-competition medical assessment (PCMA) was performed in 51 referees and assistant referees selected for the 2011 FIFA Women's World Cup. RESULTS: Family history for sudden cardiac death (SCD) was positive in four referees (7.8%), but cardiac examinations did not reveal any pathological findings. Training-unrelated ECG changes were identified in three referees (5.9%), all without correlates in echocardiography or clinical examination. Most common echocardiography findings (66.6%, n=34) were asymptomatic tricuspid and mitral regurgitations. CONCLUSIONS: During the present screening, no elite female referee was identified being at risk for SCD, and no referee had to be excluded from participating in the 2011 FIFA Women's World Cup.

Cardiac pre-competiton screening in Swiss athletes. Current situation in competitive athletes and short-time assessment of an exemplary local screening program.

AIM OF THE STUDY: In Switzerland, screening concepts for the prevention of sports-associated sudden cardiac death are still insufficiently established in the large group of competitive athletes who are not integrated in an Olympic- or other high-level squad. The aim of the present study was to objectively determine the current situation in this particular group of athletes concerning cardiac pre-competition screening and define specific features of an "ideal" Swiss screening concept. Based on these data, the feasibility and validity was tested by the implementation of an exemplary local screening programme. METHODS: A standardised questionnaire was completed by 1,047 competitive athletes of different ages and gender. The individual, sports-specific profile of an athlete and furthermore, the personal attitude towards and the vision of a "perfect" cardiac screening were assessed. Based on the results, an exemplary local screening programme for competitive athletes was implemented at the "Academic Sports Association Zurich" (ASVZ) in Zurich, Switzerland and evaluated 1 year after its introduction. RESULTS: Only 9% of the 1,047 interviewed competitive athletes (aged 13 to 64 years; median age 22 years, SD = 5.87) had previously undergone a cardiac screening. Only 47% of the interviewed competitive athletes expressed their interest to undergo a cardiac screening at all. Male and older athletes showed a significantly higher acceptance rate for the screening programme than women and younger athletes. All athletes accepted to bear the expenses for the baseline screening programme, adapted to international standards (minimal accepted fee of 60 Swiss Francs). Almost half of the athletes (49.2%) preferred easy accessibility to a sports cardiologist (max. distance of 10 kilometres). The exemplary local screening programme proved to be feasible and successful. However, only 30% of the 102 screened individuals were female and most of the athletes (80%) who made use of the screening had a specific concern or symptom (selection bias). A total of 5 athletes (4.9%) were, at least temporarily, declared as not eligible for competitive sports due to a relevant cardiac pathology. CONCLUSION: The fact that only 9% of the interviewed competitive athletes had previously undergone cardiac screening is alarming, but underlines the necessity and urgency of implementing a cost-effective and adequate screening concept in the enormous group of competitive athletes who are not integrated in an Olympic- or other high-level squad. The need for a certain self-determination and personal responsibility of the athletes should be respected. Therefore, the screening should not be mandatory. However, adequate information about the issue is crucial for an informed decision.

Echocardiographic quantification of atherosclerosis leads to cost-effective treatment with statins.

OBJECTIVE: Use of statins in prevention of atherosclerosis is effective but expensive. Patient selection gains wider public attention as medication costs in the US and Europe augment by 8% to 10% per year. We examined different clinical risk stratification strategies, particularly focusing on echocardiographic atherosclerosis quantification, for their impact on event reduction and cost-effectiveness in statin treatment. METHODS AND RESULTS: In a prospective, consecutive cohort of 336 patients referred to non-invasive cardiac examination, risk stratification was done by various combinations of risk factors and noninvasive atherosclerosis quantification. Atherosclerotic burden was determined through measuring "aortic elastance" by transthoracic echocardiogram, a validated non-invasive method. Cardiovascular events were recorded at a mean follow-up of one year. Echocardiographically determined atherosclerosis severity and event history, especially in combination, yielded the best selection strategies for statin treatment over a broad range of predetermined funding or required event reductions, surpassing conventional cardiovascular risk factors. From 26.8 statin-preventable events/1000 patients/year (assuming all patients treated), the best selection strategies could avoid: 24 with 66% of the cost for statin treatment (atherosclerosis and age criteria), 20.1 with <50% of the budget, 12.2 with <30% of the budget or 9.6 with <15% of the budget (using combinations of atherosclerosis and prior events), while conventional strategies without echo quantification of atherosclerosis were inferior. CONCLUSION: Non-invasive echocardiographic quantification of atherosclerosis improves efficiency and cost-effectiveness in statin treatment.