Variation in Utilization of Postoperative Rehabilitation After Total Hip Arthroplasty in Japan.

OBJECTIVE: The use of rehabilitation after arthroplasty in Japan is unknown. We aimed to identify utilization of postoperative rehabilitation after total hip arthroplasty (THA) and to explore the factors associated with rehabilitation usage. DESIGN: A retrospective cohort study using the National Database of Health Insurance Claims and Specific Health Checkups of Japan (NDB). SETTING: Hospitals nationwide. PARTICIPANTS: Patients aged >40 years who underwent primary THA between 2017 and 2018 (N=51,332). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: The proportion of patients who underwent postoperative rehabilitation and the number of rehabilitation days were also calculated. Patient demographic characteristics, hospital case volumes, and regions associated with continuing postoperative rehabilitation were analyzed using a Cox proportional hazards model. RESULTS: Eligible patients were selected from 3033 hospitals, of whom 41,192 (80%) were women. Of these, 94% used inpatient rehabilitation, and 20% received outpatient rehabilitation. The mean durations of rehabilitation were 47±72 days for inpatient and 195±109 days for outpatient, respectively. Large-scale hospitals performing more than 200 procedures annually had the shortest duration of inpatient rehabilitation (36-65 days) and the longest duration of outpatient rehabilitation (220-109 days) compared with smaller hospitals. The regression model consistently showed that rehabilitation continued longer at hospitals with over 200 patients per year (HR 0.96, 95% CI 0.93-0.99, P<.007). CONCLUSION: The Japanese health care system provided higher access to inpatient rehabilitation after THA than other countries. One limitation of this study is that long-term care insurance data were not analyzed. However, outpatient rehabilitation vary according to hospital case volume. Further research is needed to determine the causes of variation in rehabilitation use and the effect of variation on patient outcomes.

[Promotion of Diversity in the Academic Field of Urology : Analysis of 10,000 Articles Published in Acta Urologica Japonica during a 65-Year Period].

Gender equality is one of the most important issues in the promotion of diversity. The participation status of female urologists in academic activities has not been clarified. In the present study, we analyzed a total of 10,288 articles published by 58,914 authors in Acta Urologica Japonica since the first issue in 1955 to the present. The author's gender was determined by an application program interface for gender estimation in combination with independent manual confirmation by two researchers. The increasing rate (⊿person/⊿year) of female authors was as low as 0.067 in 1955-79, but increased to 0.400 in 1980-2000 and 0.814 in 2001-20. Over the time periods, the annual total numbers of female authors (person/year) showed an increasing trend from 3.2 in 1955-79 to 16.3 in 1980-2000 and 26.0 in 2001-20. The numbers of female author individuals, the ratio of female authors to all authors and the ratio of publications by female first author to all publications also showed similar trends. These results suggest that gender equality is becoming more prevalent in the academic field of urology. The methods and data of this study are considered to be useful for the promotion of gender equality in the academic field of urology for the future.

A survey of clarithromycin monotherapy and long-term administration of ethambutol for patients with MAC lung disease in Japan: A retrospective cohort study using the database of health insurance claims.

BACKGROUND: The number of patients with nontuberculous mycobacteriosis (NTM) has increased exponentially in recent years. In Japan, approximately 88.8% of patients with NTM suffer from Mycobacterium avium-intracellulare complex (MAC) lung disease. Incidence of MAC lung disease is increasing in particularly among the middle-aged and elderly women owing to a rapid increase in nontuberculous mycobacterial infections. General treatment for MAC lung disease is chemotherapy. The type of chemotherapy recommended by specialists to prevent the development of a drug-resistant strain of the bacteria consists of a combination of clarithromycin (CAM), rifampicin, and ethambutol (EB). CAM monotherapy is contraindicated by specialists owing to its high potential to induce drug-resistant bacterial strains in patients with MAC lung disease. In addition, administering EB at doses not less than 1000 mg d-1 is not recommended to avoid adverse drug reactions. However, it is unclear how much such treatment cases exist in real world clinical settings. This is because no long-term investigation has been carried out. MATERIALS AND METHODS: This study investigated treatment with these drugs from 2005 to 2017, by studying 1135 patients with MAC lung disease based on health insurance claims database. RESULTS: Results showed that approximately 9.2% (101 cases) were prescribed long-term CAM monotherapy for 3 months or longer and approximately 3.6% (18 cases) were prescribed high doses of EB. CONCLUSION: CAM monotherapy over a long period of time is potentially detrimental to some patients. Better awareness of the types of treatments and their potential negative effects will be beneficial to clinical practitioners.

Chemoenzymatic Posttranslational Modification Reactions for the Synthesis of Ψ[CH2 NH]-Containing Peptides.

The Ψ[CH2 NH] reduced amide bond is a peptide isostere widely used in the development of bioactive pseudopeptides. Reported here is a method of chemoenzymatic posttranslational modification for the synthesis of Ψ[CH2 NH]-containing peptides converted from ribosomally expressed peptides. The posttranslational conversion composed of an enzymatic cyclodehydration and facile two-step chemical reduction achieves deoxygenation of a specific amide bond present in a nonprotected peptide in water. This method generates the Ψ[CH2 NH] bond in peptides and is applicable to various peptide sequences, potentially enabling the preparation of a library of Ψ[CH2 NH]-containing peptides.

The prevalence and disease burden of severe eosinophilic asthma in Japan.

Background: There are limited data on the prevalence and burden of severe eosinophilic asthma (SEA) both in Japan and globally. This study aimed to assess the prevalence and burden of SEA in Japan. Methods: This study was a retrospective, observational cohort analysis using health records or health insurance claims from patients with severe asthma treated at Kyoto University Hospital. The primary outcome was the prevalence of SEA, defined as a baseline blood eosinophil count ≥300 cells/µL. Secondary outcomes included frequency and risk factors of asthma exacerbations, and asthma-related healthcare resource utilization and costs. Results: Overall, 217 patients with severe asthma were included; 160 (74%) had eosinophil assessments. Of these, 97cases (61%), 54cases (34%), and 33cases (21%) had a blood eosinophil count ≥150, ≥300, and ≥500 cells/µL, respectively. Proportion of SEA was 34%. Blood eosinophil count was not associated with a significantly increased frequency of exacerbations. In the eosinophilic group, lower % forced expiratory volume in 1 second and higher fractional exhaled nitric oxide were predictive risk factors, while the existence of exacerbation history was a predictive risk factor for asthma exacerbations in the non-eosinophilic group. Severe asthma management cost was estimated as ¥357,958/patient-year, and asthma exacerbations as ¥26,124/patient-year. Conclusions: Approximately, one-third of patients with severe asthma in Japan have SEA. While risk factors for exacerbations differed between SEA and severe non-eosinophilic asthma, both subgroups were associated with substantial disease and economic burden. From subgroup analysis, blood eosinophil counts could be an important consideration in severe asthma management.

The Improvement of the Electronic Health Record User Experience by Screen Design Principles.

The amount and complexity of data accumulated in electronic health record (EHR) is quite large, and the quantity of information that clinicians can examine and handle is very limited. Thus, it is necessary to enhance the accessibility of EHR by improving the user experience (UX). To apply information visualization that turns EHR data into an understandable visual format, we propose following five screen design principles when designing UX interfaces. #1: One view should contain single patient data. #2: Data should be summarized or titled for overview and details should be given on-demand. #3: Data should be displayed in time-series. #4: Data should be categorized by primary type. #5: More data should be displayed at the same time. Three screen designs are plausible utilizing the above-mentioned principles. To measure the UX of screen designs and validate the design principles, we built an EHR viewer system that has three windows corresponding to these screen designs and had it tested by medical staff. The results of the test revealed that the UX of the screen design is proportional to the number of design principles that the screen design incorporates. It shows that the proposed screen design principles improve the UX of EHR.

The effect of model selection on cost-effectiveness research: a comparison of kidney function-based microsimulation and disease grade-based microsimulation in chronic kidney disease modeling.

BACKGROUND: Cost effectiveness research is emerging in the chronic kidney disease (CKD) research field. Especially, an individual-level state transition model (microsimulation) is widely used for these researches. Some researchers set CKD grades as discrete health states, and the transition probabilities between these states were dependent on the CKD grades (disease grade-based microsimulation, MSM-dg), while others set estimated glomerular filtration rate value which determines the severity of CKD as a main variable describing patients' continuous status (kidney function-based microsimulation, MSM-kf). MSM-kf seems to reflect the real world more precisely but is more difficult to implement. We compared the calculation results of these two microsimulation models to evaluate the effect of model selection on CKD cost-effectiveness analysis. METHODS: We implemented simplified MSM-dg and MSM-kf emulating natural course of CKD in general, and compared models using parameters derived from an IgA nephropathy cohort. After checking these models' overall behavior, life-years, utilities, and thresholds regarding intervention costs below which the intervention is thought as dominant (V0) or cost-effective (V1) were calculated. In addition, one-way and probabilistic sensitivity analyses were performed. RESULTS: With base-case parameters, the calculated life-years was shorter in MSM-dg (73.89 vs. 75.80 years) while the thresholds were almost equal (86.87 vs. 90.43 (V0), 132.29 vs. 146.25 [V1 in 1000 USD]) compared to MSM-kf. Sensitivity analyses showed a tendency of the MSM-dg to show shorter results in life-years. V0 and V1 were distributed by approximately ±100,000 USD (V0) and ± 150,000 USD (V1) between models. CONCLUSIONS: Estimated cost-effectiveness thresholds by both models were not the same and its difference distributed too wide to be ignored. This result indicated that model selection in CKD cost-effectiveness research has large effect on their conclusions.

Analysis of the evidence-practice gap to facilitate proper medical care for the elderly: investigation, using databases, of utilization measures for National Database of Health Insurance Claims and Specific Health Checkups of Japan (NDB).

As Japan becomes a super-aging society, presentation of the best ways to provide medical care for the elderly, and the direction of that care, are important national issues. Elderly people have multi-morbidity with numerous medical conditions and use many medical resources for complex treatment patterns. This increases the likelihood of inappropriate medical practices and an evidence-practice gap. The present study aimed to: derive findings that are applicable to policy from an elucidation of the actual state of medical care for the elderly; establish a foundation for the utilization of National Database of Health Insurance Claims and Specific Health Checkups of Japan (NDB), and present measures for the utilization of existing databases in parallel with NDB validation.Cross-sectional and retrospective cohort studies were conducted using the NDB built by the Ministry of Health, Labor and Welfare of Japan, private health insurance claims databases, and the Kyoto University Hospital database (including related hospitals). Medical practices (drug prescription, interventional procedures, testing) related to four issues-potential inappropriate medication, cancer therapy, chronic kidney disease treatment, and end-of-life care-will be described. The relationships between these issues and clinical outcomes (death, initiation of dialysis and other adverse events) will be evaluated, if possible.

Effect of a Kinect-based exercise game on improving executive cognitive performance in community-dwelling elderly: case control study.

BACKGROUND: Decrease of dual-task (DT) ability is known to be one of the risk factors for falls. We developed a new game concept, Dual-Task Tai Chi (DTTC), using Microsoft's motion-capture device Kinect, and demonstrated that the DTTC test can quantitatively evaluate various functions that are known risk factors for falling in elderly adults. Moreover, DT training has been attracting attention as a way to improve balance and DT ability. However, only a few studies have reported that it improves cognitive performance. OBJECTIVE: The purpose of this study was to demonstrate whether or not a 12-week program of DTTC training would effectively improve cognitive functions. METHODS: This study examined cognitive functions in community-dwelling older adults before and after 12 weeks of DTTC training (training group [TG]) or standardized training (control group [CG]). Primary end points were based on the difference in cognitive functions between the TG and the CG. Cognitive functions were evaluated using the trail-making test (part A and part B) and verbal fluency test. RESULTS: A total of 41 elderly individuals (TG: n=26, CG: n=15) participated in this study and their cognitive functions were assessed before and after DTTC training. Significant differences were observed between the two groups with significant group × time interactions for the executive cognitive function measure, the delta-trail-making test (part B-part A; F1,36=4.94, P=.03; TG: pre mean 48.8 [SD 43.9], post mean 42.2 [SD 29.0]; CG: pre mean 49.5 [SD 51.8], post mean 64.9 [SD 54.7]). CONCLUSIONS: The results suggest that DTTC training is effective for improving executive cognitive functions. TRIAL REGISTRATION: Japan Medical Association Clinical Trial Registration Number: JMA-IIA00092; https://dbcentre3.jmacct.med.or.jp/jmactr/App/JMACTRS06/JMACTRS06.aspx?seqno=2682 (Archived by WebCite at http://www.webcitation.org/6NRtOkZFh).

Development of a methodology for the detection of hospital financial outliers using information systems.

Comparison of financial indices helps to illustrate differences in operations and efficiency among similar hospitals. Outlier data tend to influence statistical indices, and so detection of outliers is desirable. Development of a methodology for financial outlier detection using information systems will help to reduce the time and effort required, eliminate the subjective elements in detection of outlier data, and improve the efficiency and quality of analysis. The purpose of this research was to develop such a methodology. Financial outliers were defined based on a case model. An outlier-detection method using the distances between cases in multi-dimensional space is proposed. Experiments using three diagnosis groups indicated successful detection of cases for which the profitability and income structure differed from other cases. Therefore, the method proposed here can be used to detect outliers.

Health Care Worker Usage of Large-Scale Health Information Exchanges in Japan: User-Level Audit Log Analysis Study.

Background: Over 200 health information exchanges (HIEs) are currently operational in Japan. The most common feature of HIEs is remote on-demand viewing or searching of aggregated patient health data from multiple institutions. However, the usage of this feature by individual users and institutions remains unknown. Objective: This study aims to understand usage of the on-demand patient data viewing feature of large-scale HIEs by individual health care workers and institutions in Japan. Methods: We conducted audit log analyses of large-scale HIEs. The research subjects were HIEs connected to over 100 institutions and with over 10,000 patients. Each health care worker's profile and audit log data for HIEs were collected. We conducted four types of analyses on the extracted audit log. First, we calculated the ratio of the number of days of active HIE use for each hospital-affiliated doctor account. Second, we calculated cumulative monthly usage days of HIEs by each institution in financial year (FY) 2021/22. Third, we calculated each facility type's monthly active institution ratio in FY2021/22. Fourth, we compared the monthly active institution ratio by medical institution for each HIE and the proportion of cumulative usage days by user type for each HIE. Results: We identified 24 HIEs as candidates for data collection and we analyzed data from 7 HIEs. Among hospital doctors, 93.5% (7326/7833) had never used HIEs during the available period in FY2021/22, while 19 doctors used them at least 30% of days. The median (IQR) monthly active institution ratios were 0.482 (0.470-0.487) for hospitals, 0.243 (0.230-0.247) for medical clinics, and 0.030 (0.024-0.048) for dental clinics. In 51.9% (1781/3434) of hospitals, the cumulative monthly usage days of HIEs was 0, while in 26.8% (921/3434) of hospitals, it was between 1 and 10, and in 3% (103/3434) of hospitals, it was 100 or more. The median (IQR) monthly active institution ratio in medical institutions was 0.511 (0.487-0.529) for the most used HIE and 0.109 (0.0927-0.117) for the least used. The proportion of cumulative usage days of HIE by user type was complex for each HIE, and no consistent trends could be discerned. Conclusions: In the large-scale HIEs surveyed in this study, the overall usage of the on-demand patient data viewing feature was low, consistent with past official reports. User-level analyses of audit logs revealed large disparities in the number of days of HIE use among health care workers and institutions. There were also large disparities in HIE use by facility type or HIE; the percentage of cumulative HIE usage days by user type also differed by HIE. This study indicates the need for further research into why there are large disparities in demand for HIEs in Japan as well as the need to design comprehensive audit logs that can be matched with other official datasets.

Investigation of Radiologist Diagnostic Difficulty Prediction Without CT Images.

For better collaboration among radiologists, the interpretation workload should be evaluated, considering the difference in difficulty for interpreting each case. However, objective evaluation of difficulty is challenging. This study proposes a multimodal classifier of structural and textual data to predict difficulty based on order information and patient data without using images. The classifier showed performance with a specificity of 0.9 and an accuracy of 0.7.

Medical resource usage for COVID-19 evaluated using the National Database of Health Insurance Claims and Specific Health Checkups of Japan.

PURPOSE: The coronavirus disease 2019 (COVID-19) pandemic exhibited several different waves threatening global health care. During this pandemic, medical resources were depleted. However, the kind of medical resources provided to each wave was not clarified. This study aimed to examine the characteristics of medical care provision at COVID-19 peaks in preparation for the next pandemic. METHODS: Using medical insurance claim records in Japan, we examined the presence or absence of COVID-19 infection and the use of medical resources for all patients monthly by age group. RESULTS: The wave around August 2021 with the Delta strain had the strongest impact on the working population in terms of hospital admission and respiratory support. For healthcare providers, this peak had the highest frequency of severely ill patients. In the subsequent wave, although the number of patients with COVID-19 remained high, they were predominantly older adults, with relatively fewer patients receiving intensive care. CONCLUSIONS: In future pandemics, we should refer to the wave around August 2021 as a situation of medical resource shortage resulting from the COVID-19 pandemic.

Individual Activity Anomaly Estimation in Operating Rooms Based on Time-Sequential Prediction.

Surveillance videos of operating rooms have potential to benefit post-operative analysis and study. However, there is currently no effective method to extract useful information from the long and massive videos. As a step towards tackling this issue, we propose a novel method to recognize and evaluate individual activities using an anomaly estimation model based on time-sequential prediction. We verified the effectiveness of our method by comparing two time-sequential features: individual bounding boxes and body key points. Experiment results using actual surgery videos show that the bounding boxes are suitable for predicting and detecting regional movements, while the anomaly scores using key points can hardly be used to detect activities. As future work, we will be proceeding with extending our activity prediction for detecting unexpected and urgent events.

Similarity Analysis of Clinical Notes for Revealing Writing Styles in an Electronic Medical Record System.

BACKGROUND: One of the disadvantages of medical documentation in Electronic Medical Record (EMR) systems is that records tend to be redundant by "copying and pasting", a writing style to duplicate and revise previous records. In this study, we analyzed the similarity between records to identify the factors affecting the writing style of clinical notes. METHOD: We analyzed 98,038 records of 4,149 patients from two years in the Department of Obstetricians and Gynecology at Kyoto University Hospital, Japan. We observed the correlation between the distribution of the record similarity and string amounts, as well as the disease codes and ratios of outpatient visit. RESULTS: The patient group with high record similarity and large number of strings was the group with reproductive medicine, followed by the group of malignant tumor follow-up or Women's Healthcare. DISCUSSION: In reproductive medicine, physicians have a demand for an overarching evaluation, and in follow-up malignancies or in Women's Healthcare, they have a demand to check for subtle differences from the last time. These facts along with our data insist that the writing style in EMR systems is related to the patient's status. CONCLUSION: We declared that the writing style in EMR systems is affected by the patient's status. The writing style of duplicating and revising is preferred (1) when there is a clinical demand for an overarching evaluation, and (2) when there is a clinical demand to check for subtle differences from the last time.

Developing a Sustainable Shared Child's Health Record in Low Resources Setting, Lao PDR.

Lao PDR's Ministry of Health has problem with fragmented data, lack of standardization, and inability to interoperate hinder child health data collection. Electronic health information exchange (HIE) could improve data quality and shared child health records (SCHR). In this study we developed the SCHR by interoperating with existing healthcare systems. The FHIR IPS standards were customized based on data elements. 14 experts from the technical working group (TWG) had determined the minimum dataset for data transactions and system testing was analyzed on the HAPI FHIR server. Used FHIR IPS standards for interoperability within Client Registry (CR-DHIS2), Electronic Immunization Record (EIR-DHIS2) and Electronic Medical Record (EMR) works well for data transactions. The initial result of the SCHR could be able to provide a real target child and to monitor full vaccination. However, prior to the actual deployment of the system, it is necessary to validate it and guarantee the confidentiality and safety of the data.

Investigating Decision Factors Affecting Subjective Description Disclosure in Health Information Exchange in Japan.

Despite the perceived advantages of health information exchange (HIE), their utilization has been stagnant, and a detailed survey at the regional level is needed to address this issue. We conducted interviews with operators of HIEs in operation in Japan as a pilot study and found that subjective descriptions by healthcare professionals contained in clinical notes are frequently referenced in HIEs. Currently, however, only a limited number of medical institutions in Japan disclose subjective descriptions. In this study, we aim to clarify the factors that influence whether or not to disclose subjective descriptions through an interview survey. Although the final results are yet to be determined, it is anticipated that the non-disclosing medical institutions will show negative aspects of disclosure, such as privacy concerns and misuse of information. Addressing the concerns raised in this study is important for the future dissemination of HIE.

Comparing Patient Perception and Physician's Records: Generative AI Performance Evaluation.

Patient perception involves a patient's thoughts and beliefs regarding their health status. It is also associated with medical compliance and outcomes. However, discrepancies often arise between patient perception and physicians' documentation within the medical records, resulting in misunderstanding and suboptimal doctor-patient communication. In this study, we assessed the efficacy of generative artificial intelligence (AI) in comparing the content of patient perception as recorded in patient questionnaires and physicians' records of the Department of Breast Surgery. We evaluated the precision and recall of the generative AI by comparison with human-created ground truth. Our results demonstrated the high performance of the generative AI in comprehending and contrasting symptoms and the entire content recorded differently by patients and physicians, with F1 scores ranging from 0.77 to 0.97. These results highlight the potential contribution of a generative AI to deeper mutual comprehension in healthcare scenarios.

Gamification Approach to Provide Support About the Deferral Experience in Blood Donation: Design and Feasibility Study.

BACKGROUND: Multiple studies have examined the impact of deferral on the motivation of prospective blood donors, proposing various policies and strategies to support individuals who undergo this experience. However, existing information and communications technology systems focused on blood donation have not yet integrated these ideas or provided options to assist with the deferral experience. OBJECTIVE: This study aims to propose an initial gamified design aimed at mitigating the impact of the deferral experience by addressing the drivers of awareness and knowledge, interaction and validation, and motivation. Additionally, the study explores the feasibility of implementing such a system for potential users. METHODS: We conducted a literature review focusing on the dynamics of motivation and intention related to blood donation, as well as the deferral situation and its impact on citizens. Through this review, we identified weak donor identity, lack of knowledge, and reduced motivation as key factors requiring support from appropriate interventions. These factors were then defined as our key drivers. Taking these into account, we proposed a gamification approach that incorporates concepts from the MDA framework. The aim is to stimulate the aforementioned drivers and expand the concept of contribution and identity in blood donation. For a preliminary evaluation, we designed a prototype to collect feedback on usability, usefulness, and interest regarding a potential implementation of our proposed gamification approach. RESULTS: Among the participants, a total of 11 citizens interacted with the app and provided feedback through our survey. They indicated that interacting with the app was relatively easy, with an average score of 4.13 out of 5 when considering the 11 tasks of interaction. The SUS results yielded a final average score of 70.91 from the participants' answers. Positive responses were received when participants were asked about liking the concept of the app (3.82), being likely to download it (3.55), and being likely to recommend it to others (3.64). Participants expressed positivity about the implementation of the design but also highlighted current shortcomings and suggested possible improvements in both functionality and usability. CONCLUSIONS: Although deferral is a common issue in blood donation, there is a missed opportunity in existing ICT services regarding how to effectively handle such experiences. Our proposed design and implementation seem to have captured the interest of prospective users due to its perceived positive usefulness and potential. However, further confirmation is needed. Improving the design of activities that currently rely heavily on extrinsic motivation elements and integrating more social components to create an enhanced activity loop for intrinsic motivation could further increase the value of the proposed project. Future research could involve conducting a more specialized and longitudinal design evaluation with a larger sample size.

Early Diagnosis of Hereditary Angioedema in Japan Based on a US Medical Dataset: Algorithm Development and Validation.

BACKGROUND: Hereditary angioedema (HAE), a rare genetic disease, induces acute attacks of swelling in various regions of the body. Its prevalence is estimated to be 1 in 50,000 people, with no reported bias among different ethnic groups. However, considering the estimated prevalence, the number of patients in Japan diagnosed with HAE remains approximately 1 in 250,000, which means that only 20% of potential HAE cases are identified. OBJECTIVE: This study aimed to develop an artificial intelligence (AI) model that can detect patients with suspected HAE using medical history data (medical claims, prescriptions, and electronic medical records [EMRs]) in the United States. We also aimed to validate the detection performance of the model for HAE cases using the Japanese dataset. METHODS: The HAE patient and control groups were identified using the US claims and EMR datasets. We analyzed the characteristics of the diagnostic history of patients with HAE and developed an AI model to predict the probability of HAE based on a generalized linear model and bootstrap method. The model was then applied to the EMR data of the Kyoto University Hospital to verify its applicability to the Japanese dataset. RESULTS: Precision and sensitivity were measured to validate the model performance. Using the comprehensive US dataset, the precision score was 2% in the initial model development step. Our model can screen out suspected patients, where 1 in 50 of these patients have HAE. In addition, in the validation step with Japanese EMR data, the precision score was 23.6%, which exceeded our expectations. We achieved a sensitivity score of 61.5% for the US dataset and 37.6% for the validation exercise using data from a single Japanese hospital. Overall, our model could predict patients with typical HAE symptoms. CONCLUSIONS: This study indicates that our AI model can detect HAE in patients with typical symptoms and is effective in Japanese data. However, further prospective clinical studies are required to investigate whether this model can be used to diagnose HAE.