Development of novel optical character recognition system to reduce recording time for vital signs and prescriptions: A simulation-based study

Digital advancements can reduce the burden of recording clinical information. This intra-subject experimental study compared the time and error rates for recording vital signs and prescriptions between an optical character reader (OCR) and manual typing. This study was conducted at three community hospitals and two fire departments in Japan. Thirty-eight volunteers (15 paramedics, 10 nurses, and 13 physicians) participated in the study. We prepared six sample pictures: three ambulance monitors for vital signs (normal, abnormal, and shock) and three pharmacy notebooks that provided prescriptions (two, four, or six medications). The participants recorded the data for each picture using an OCR or by manually typing on a smartphone. The outcomes were recording time and error rate defined as the number of characters with omissions or misrecognitions/misspellings of the total number of characters. Data were analyzed using paired Wilcoxon signed-rank sum and McNemar's tests. The recording times for vital signs were similar between groups (normal state, 21 s [interquartile range (IQR), 17-26 s] for OCR vs. 23 s [IQR, 18-31 s] for manual typing). In contrast, prescription recording was faster with the OCR (e.g., six-medication list, 18 s [IQR, 14-21 s] for OCR vs. 144 s [IQR, 112-187 s] for manual typing). The OCR had fewer errors than manual typing for both vital signs and prescriptions (0/1056 [0%] vs. 14/1056 [1.32%]; p<0.001 and 30/4814 [0.62%] vs. 53/4814 [1.10%], respectively). In conclusion, the developed OCR reduced the recording time for prescriptions but not vital signs. The OCR showed lower error rates than manual typing for both vital signs and prescription data.

Acceptance, barriers and facilitators to implementing AI-based decision support systems in emergency departments: a quantitative and qualitative evaluation (Preprint)

Background

Despite the increasing availability of clinical decision support systems (CDSSs) and rising expectation for CDSSs based on artificial intelligence (AI), little is known about the acceptance of AI-based CDSS by physicians and its barriers and facilitators in emergency care settings.

Objective

We aimed to evaluate the acceptance, barriers, and facilitators to implementing AI-based CDSSs in the emergency care setting through the opinions of physicians on our newly developed, real-time AI-based CDSS, which alerts ED physicians by predicting aortic dissection based on numeric and text information from medical charts, by using the Unified Theory of Acceptance and Use of Technology (UTAUT; for quantitative evaluation) and the Consolidated Framework for Implementation Research (CFIR; for qualitative evaluation) frameworks.

Methods

This mixed methods study was performed from March to April 2021. Transitional year residents (n=6), emergency medicine residents (n=5), and emergency physicians (n=3) from two community, tertiary care hospitals in Japan were included. We first developed a real-time CDSS for predicting aortic dissection based on numeric and text information from medical charts (eg, chief complaints, medical history, vital signs) with natural language processing. This system was deployed on the internet, and the participants used the system with clinical vignettes of model cases. Participants were then involved in a mixed methods evaluation consisting of a UTAUT-based questionnaire with a 5-point Likert scale (quantitative) and a CFIR-based semistructured interview (qualitative). Cronbach α was calculated as a reliability estimate for UTAUT subconstructs. Interviews were sampled, transcribed, and analyzed using the MaxQDA software. The framework analysis approach was used during the study to determine the relevance of the CFIR constructs.

Results

All 14 participants completed the questionnaires and interviews. Quantitative analysis revealed generally positive responses for user acceptance with all scores above the neutral score of 3.0. In addition, the mixed methods analysis identified two significant barriers (System Performance, Compatibility) and two major facilitators (Evidence Strength, Design Quality) for implementation of AI-based CDSSs in emergency care settings.

Conclusions

Our mixed methods evaluation based on theoretically grounded frameworks revealed the acceptance, barriers, and facilitators of implementation of AI-based CDSS. Although the concern of system failure and overtrusting of the system could be barriers to implementation, the locality of the system and designing an intuitive user interface could likely facilitate the use of optimal AI-based CDSS. Alleviating and resolving these factors should be key to achieving good user acceptance of AI-based CDSS.

Risk factors of sepsis among patients with qSOFA<2 in the emergency department

OBJECTIVE

Studies have suggested that qSOFA can be used for early detection of sepsis immediately upon arrival at the emergency department (ED). Despite this, little is known about the risk factors associated with the subsequent diagnosis of sepsis among patients with qSOFA<2 in the ED.

METHODS

This is a retrospective cohort study using ED data from a large tertiary medical center in Japan, 2018-2020. We included adult patients (aged ≥18 years) presenting to the ED with suspected infection (e.g., having a fever) and qSOFA<2. We identified patients who developed sepsis based on the Sepsis-3 criteria, and compared patient characteristics (e.g., demographics, vital signs upon the initial triage, chief complaint, and comorbidities) between patients who developed sepsis or not. Additionally, we identified the potential risk factors of sepsis among patients with qSOFA<2 using a multivariable logistic regression model.

RESULTS

We identified 151 (7%) patients who developed sepsis among 2025 adult patients with suspected infection and qSOFA<2. Compared with patients who did not develop sepsis, patients who developed sepsis were likely to be older and have vital signs suggestive of imminent sepsis (e.g., high respiratory rate). In the multivariable logistic regression model, the potential risk factors of sepsis among patients with qSOFA<2 were older age (adjusted OR, 1.92 [95%CI 1.19-3.19]), vital signs suggestive of imminent sepsis (e.g., adjusted OR of altered mental status, 3.50 [95%CI 2.25-5.50]), receipt of oxygen therapy upon arrival at the ED (adjusted OR, 1.91 [95%CI 1.38-2.26]), chief complaint of sore throat (adjusted OR, 2.15 [95%CI 1.08-4.13]), and the presence of comorbid diabetes mellitus, ischemic heart disease, and chronic kidney disease (e.g., adjusted OR of diabetes mellitus, 1.47 [95%CI 1.10-1.96]). On the contrary, chief complaint of abdominal and chest pain were associated with a lower risk of sepsis (e.g., adjusted OR of abdominal pain, 0.26 [95%CI 0.14-0.45]).

CONCLUSIONS

We found that older age, vital signs prognosticating sepsis, and the presence of some comorbidities were the potential risk factors of sepsis in patients with qSOFA<2. These potential risk factors could be useful to efficiently recognize patients who might develop sepsis in the ED.

Initial assessment in emergency departments by chief complaint and respiratory rate

BACKGROUND

Understanding heterogeneity of the respiratory rate (RR) as a risk stratification marker across chief complaints is important to reduce misinterpretation of the risk posed by outcome events and to build accurate risk stratification tools. This study was conducted to investigate the associations between RR and clinical outcomes according to the five most frequent chief complaints in an emergency department (ED): fever, shortness of breath, altered mental status, chest pain, and abdominal pain.

METHODS

This retrospective cohort study examined ED data of all adult patients who visited the ED of a tertiary medical center during April 2018-September 2019. The primary exposure was RR at the ED visit. Outcome measures were hospitalization and mechanical ventilation use. We used restrictive cubic spline and logistic regression models to assess the association of interest.

RESULTS

Of 16 956 eligible ED patients, 4926 (29%) required hospitalization; 448 (3%) required mechanical ventilation. Overall, U-shaped associations were found between RR and the risk of hospitalization (eg, using RR = 16 as the reference, the odds ratio [OR] of RR = 32, 6.57 [95% CI 5.87-7.37]) and between RR and the risk of mechanical ventilation. This U-shaped association was driven by patients' association with altered mental status (eg, OR of RR = 12, 2.63 [95% CI 1.25-5.53]). For patients who have fever or shortness of breath, the risk of hospitalization increased monotonously with increased RR.

CONCLUSIONS

U-shaped associations of RR with the risk of overall clinical outcomes were found. These associations varied across chief complaints.

Association of Initial Potassium Levels with the Type of Stroke in the Emergency Department

Serum potassium levels are considered as a marker of cerebrovascular emergencies but there is less clarity on the association between initial serum potassium levels recorded on patient's arrival at the emergency department with the type of stroke. This is a case-control study using data of a tertiary care hospital in Japan from April 2018 to September 2019. We identified adult patients with hemorrhagic stroke including subarachnoid hemorrhage (cases) and those with ischemic stroke (controls). Data on age, sex, chief complaints, vital signs, and initial blood tests were collected. We analyzed the association between serum potassium levels and the type of stroke by drawing a LOWESS curve. Additionally, we fitted a logistic regression model to examine the association of interest. There were 416 stroke patients (158 hemorrhagic and 258 ischemic). The median age was 77 years (IQR: 68, 84), and 54% were male. The mean potassium level was 3.69 ± 0.55 mEq/L for hemorrhagic stroke and 4.08 ± 0.65 mEq/L for ischemic stroke. The LOWESS curve showed that the lower initial potassium level was linearly associated with a greater likelihood of hemorrhagic stroke. In the logistic regression model, the odds ratio for the risk of hemorrhagic stroke per 1 mEq/L lower potassium level was 3.31 (95% confidence interval [CI]: 2.24-5.04). This association remained significant in a multivariable model adjusting for other covariates (OR: 2.62 [95% CI: 1.70-4.16]). Initial potassium level was lower in patients with hemorrhagic stroke compared to those with ischemic stroke.

Clinical performance of early warning scoring systems for identifying sepsis among anti-hypertensive agent users

BACKGROUND

Little is known about the accuracy of the quick Sequential Organ Failure Assessment (qSOFA) and the National Early Warning Score (NEWS) in identifying sepsis patients with a history of hypertension on anti-hypertensive agents, which affect vital signs as components of the scoring systems. We aimed to examine the ability of qSOFA and NEWS to predict sepsis among anti-hypertensive agent users by comparing them with non-users.

METHODS

We retrospectively identified adult patients (aged ≥18years) with suspected infection who presented to an emergency department (ED) of a large tertiary medical center in Japan between April 2018 and March 2020. Suspected infection was defined based on the chief complaint of fever, high body temperature, or the clinical context on arrival at the ED. We excluded patients who had trauma or cardiac arrest, those who were transported to other hospitals after arrival at the ED, and those whose vital signs data were mostly missing. The predictive performances of qSOFA and NEWS based on initial vital signs were examined separately for sepsis, ICU admission, and in-hospital mortality and compared between anti-hypertensive agent users and non-users.

RESULTS

Among 2900 patients with suspected infection presenting to the ED, 291 (10%) had sepsis, 1023 (35%) were admitted to the ICU, and 188 (6.5%) died. The prediction performances of qSOFA and NEWS for each outcome among anti-hypertensive agent users were lower than that among non-users (e.g., c-statistics of qSOFA for sepsis, 0.66 vs. 0.71, p = 0.07; and for ICU admission, 0.70 vs. 0.75, p = 0.01). For identifying sepsis, the sensitivity and specificity of qSOFA ≥2 were 0.43 and 0.77 in anti-hypertensive agent users and 0.51 and 0.82 in non-users. Similar associations were observed for identifying ICU admission and in-hospital mortality. Regardless of the use of anti-hypertensive agents, NEWS had better prediction abilities for each outcome than qSOFA.

CONCLUSION

The clinical performance of qSOFA and NEWS for identifying sepsis among anti-hypertensive agent users was likely lower than that among non-users.

Association between the use of physical restraint and functional decline among older inpatients admitted with pneumonia in an acute care hospital: A retrospective cohort study

AIM

This study was conducted to investigate the association between the use of physical restraint and functional decline in older inpatients admitted with pneumonia in an acute care setting. Although several adverse effects related to restraint use have been reported, few researchers have examined this subject in acute care settings.

METHODS

This retrospective cohort study was conducted at a 471-bed, acute care hospital in Japan. Patients 65 years old and older who were admitted with pneumonia between April 2015 and September 2017 were included. The use of restraints (belts and/or mittens) was recorded for every 8-hour shift. The number of shifts during which each patient was restrained was used as an explanatory variable. The primary outcome was the Katz ADL score at discharge. We used multiple linear regression analysis to adjust for confounding factors.

RESULTS

Of 403 patients, 94 required physical restraints. The mean age was 84.5 years (standard deviation [SD] 8.2); 44.4% were women. The mean Katz score on admission was 2.7 (SD 2.4). For multiple linear regression analysis, the coefficient of the number of restraints used was -0.024 (95% confidence interval: -0.044, -0.003, p = .022). Consequently, the restraint use for 13.9 days was associated with the decrease in the Katz score by 1.0.

CONCLUSIONS

Results suggest that physical restraint use is associated with functional decline among older inpatients admitted with pneumonia in acute care settings.

Validation of chief complaints, medical history, medications, and physician diagnoses structured with an integrated emergency department information system in Japan: the Next Stage ER system

Aim

Emergency department information systems (EDIS) facilitate free‐text data use for clinical research; however, no study has validated whether the Next Stage ER system (NSER), an EDIS used in Japan, accurately translates electronic medical records (EMRs) into structured data.

Methods

This is a retrospective cohort study using data from the emergency department (ED) of a tertiary care hospital from 2018 to 2019. We used EMRs of 500 random samples from 27,000 ED visits during the study period. Through the NSER system, chief complaints were translated into 231 chief complaint categories based on the Japan Triage and Acuity Scale. Medical history and physician’s diagnoses were encoded using the International Classification of Diseases, 10th Revision; medications were encoded as Anatomical Therapeutic Chemical Classification System codes. Two reviewers independently reviewed 20 items (e.g., presence of fever) for each study component (e.g., chief complaints). We calculated association measures of the structured data by the NSER system, using the chart review results as the gold standard.

Results

Sensitivities were very high (>90%) in 17 chief complaints. Positive predictive values were high for 14 chief complaints (≥80%). Negative predictive values were ≥96% for all chief complaints. For medical history and medications, most of the association measures were very high (>90%). For physicians’ ED diagnoses, sensitivities were very high (>93%) in 16 diagnoses; specificities and negative predictive values were very high (>97%).

Conclusions

Chief complaints, medical history, medications, and physician’s ED diagnoses in EMRs were well‐translated into existing categories or coding by the NSER system.