Search

Your search keyword '"Horiguchi, Hiromasa"' showing total 848 results
Start Over Author "Horiguchi, Hiromasa"
848 results on '"Horiguchi, Hiromasa"'

1. Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?

Author

Ando, Kenichiro, Komachi, Mamoru, Okumura, Takashi, Horiguchi, Hiromasa, and Matsumoto, Yuji

Subjects
Computer Science - Computation and Language
Abstract

During the patient's hospitalization, the physician must record daily observations of the patient and summarize them into a brief document called "discharge summary" when the patient is discharged. Automated generation of discharge summary can greatly relieve the physicians' burden, and has been addressed recently in the research community. Most previous studies of discharge summary generation using the sequence-to-sequence architecture focus on only inpatient notes for input. However, electric health records (EHR) also have rich structured metadata (e.g., hospital, physician, disease, length of stay, etc.) that might be useful. This paper investigates the effectiveness of medical meta-information for summarization tasks. We obtain four types of meta-information from the EHR systems and encode each meta-information into a sequence-to-sequence model. Using Japanese EHRs, meta-information encoded models increased ROUGE-1 by up to 4.45 points and BERTScore by 3.77 points over the vanilla Longformer. Also, we found that the encoded meta-information improves the precisions of its related terms in the outputs. Our results showed the benefit of the use of medical meta-information.

Published
2023
Full Text
View/download PDF

2. Exploring Optimal Granularity for Extractive Summarization of Unstructured Health Records: Analysis of the Largest Multi-Institutional Archive of Health Records in Japan

Author

Ando, Kenichiro, Okumura, Takashi, Komachi, Mamoru, Horiguchi, Hiromasa, and Matsumoto, Yuji

Subjects
Computer Science - Computation and Language
Abstract

Automated summarization of clinical texts can reduce the burden of medical professionals. "Discharge summaries" are one promising application of the summarization, because they can be generated from daily inpatient records. Our preliminary experiment suggests that 20-31% of the descriptions in discharge summaries overlap with the content of the inpatient records. However, it remains unclear how the summaries should be generated from the unstructured source. To decompose the physician's summarization process, this study aimed to identify the optimal granularity in summarization. We first defined three types of summarization units with different granularities to compare the performance of the discharge summary generation: whole sentences, clinical segments, and clauses. We defined clinical segments in this study, aiming to express the smallest medically meaningful concepts. To obtain the clinical segments, it was necessary to automatically split the texts in the first stage of the pipeline. Accordingly, we compared rule-based methods and a machine learning method, and the latter outperformed the formers with an F1 score of 0.846 in the splitting task. Next, we experimentally measured the accuracy of extractive summarization using the three types of units, based on the ROUGE-1 metric, on a multi-institutional national archive of health records in Japan. The measured accuracies of extractive summarization using whole sentences, clinical segments, and clauses were 31.91, 36.15, and 25.18, respectively. We found that the clinical segments yielded higher accuracy than sentences and clauses. This result indicates that summarization of inpatient records demands finer granularity than sentence-oriented processing. Although we used only Japanese health records, it can be interpreted as follows: physicians extract "concepts of medical significance" from patient records and recombine them ...

Published
2022
Full Text
View/download PDF

5. Usefulness of a pluralistic approach in sentinel surveillance: seasonal influenza activity based on case counts per sentinel site in the National Epidemiological Surveillance of Infectious Diseases Program and test counts, case counts, and test positivity from the National Hospital Organization

Author

Arashiro, Takeshi, primary, Arima, Yuzo, additional, Takahashi, Takuri, additional, Taniguchi, Kiyosu, additional, Horiguchi, Hiromasa, additional, and Suzuki, Motoi, additional

Published
2024
Full Text
View/download PDF

10. Association between hospital case volume and mortality in non-elderly pneumonia patients stratified by severity: a retrospective cohort study

Author

Kumamaru, Hiraku, Tsugawa, Yusuke, Horiguchi, Hiromasa, Kumamaru, Kanako Kunishima, Hashimoto, Hideki, and Yasunaga, Hideo

Subjects
Health Services and Systems, Nursing, Public Health, Health Sciences, Pneumonia, Lung, Clinical Research, Pneumonia & Influenza, Aging, 4.1 Discovery and preclinical testing of markers and technologies, Detection, screening and diagnosis, Good Health and Well Being, Adolescent, Adult, Female, Hospitalization, Humans, Japan, Length of Stay, Male, Middle Aged, Outcome Assessment, Health Care, Retrospective Studies, Risk Assessment, Severity of Illness Index, Age-factors, Hospital volume, Mortality, Non-elderly, Quality of care, Effect modification, Library and Information Studies, Public Health and Health Services, Health Policy & Services, Health services and systems, Public health
Abstract

BackgroundThe characteristics and aetiology of pneumonia in the non-elderly population is distinct from that in the elderly population. While a few studies have reported an inverse association between hospital case volume and clinical outcome in elderly pneumonia patients, the evidence is lacking in a younger population. In addition, the relationship between volume and outcome may be different in severe pneumonia cases than in mild cases. In this context, we tested two hypotheses: 1) non-elderly pneumonia patients treated at hospitals with larger case volume have better clinical outcome compared with those treated at lower case volume hospitals; 2) the volume-outcome relationship differs by the severity of the pneumonia.MethodsWe conducted the study using the Japanese Diagnosis Procedure Combination database. Patients aged 18-64 years discharged from the participating hospitals between July to December 2010 were included. The hospitals were categorized into four groups (very-low, low, medium, high) based on volume quartiles. The association between hospital case volume and in-hospital mortality was evaluated using multivariate logistic regression with generalized estimating equations adjusting for pneumonia severity, patient demographics and comorbidity score, and hospital academic status. We further analyzed the relationship by modified A-DROP pneumonia severity score calculated using the four severity indices: dehydration, low oxygen saturation, orientation disturbance, and decreased systolic blood pressure.ResultsWe identified 8,293 cases of pneumonia at 896 hospitals across Japan, with 273 in-hospital deaths (3.3%). In the overall population, no significant association between hospital volume and in-hospital mortality was observed. However, when stratified by pneumonia severity score, higher hospital volume was associated with lower in-hospital mortality at the intermediate severity level (modified A-DROP score = 2) (odds ratio (OR) of very low vs. high: 2.70; 95% confidence interval (CI): 1.12-6.55, OR of low vs. high: 2.40; 95% CI:0.99-5.83). No significant association was observed for other severity strata.ConclusionsHospital case volume was inversely associated with in-hospital mortality in non-elderly pneumonia patients with intermediate pneumonia severity. Our result suggests room for potential improvement in the quality of care in hospitals with lower volume, to improve treatment outcomes particularly in patients admitted with intermediate pneumonia severity.

Published
2014

22. Risk of Underlying Diseases and Effectiveness of Drugs on COVID-19 Inpatients Assessed Using Medical Claims in Japan: Retrospective Observational Study

Author

Mitsushima,Shingo, Horiguchi,Hiromasa, Taniguchi,Kiyosu, Mitsushima,Shingo, Horiguchi,Hiromasa, and Taniguchi,Kiyosu

Abstract

Shingo Mitsushima,1 Hiromasa Horiguchi,2 Kiyosu Taniguchi3,4 1Center for Field Epidemic Intelligence, Research and Professional Development, National Institute of Infectious Diseases, Shinjuku-ku, Tokyo, Japan; 2Department of Clinical Data Management and Research, Clinical Research Center, National Hospital Organization Headquarters, Meguro-ku, Tokyo, Japan; 3Director-General, National Hospital Organization Mie National Hospital, Tsu, Mie, Japan; 4Research Director, The Tokyo Foundation for Policy Research, Minato-ku, Tokyo, JapanCorrespondence: Shingo Mitsushima, Center for Field Epidemic Intelligence, Research and Professional Development, National Institute of Infectious Diseases, 1-23-1 Toyama, Shinjuku-ku, Tokyo, 162-8640, Japan, Tel +81-3-5285-1111, Fax +81-3-5285-1150, Email mitsushi@niid.go.jpBackground: Results of earlier studies have demonstrated underlying diseases such as cancer, diabetes mellitus, immunodeficiency, hypertension and heart failure to be risk factors for severe outcomes and mortality. Furthermore, clinical trials have shown that drugs such as antiviral drugs, antibody cocktails, steroids and anti-inflammatory drugs can be expected to prevent severe COVID-19 outcomes and death.Methods: This study, using inpatient records from the Medical Information Analysis Databank covering national hospital organizations in Japan, was conducted to evaluate the effects of underlying diseases and/or administered drugs on mortality. Subjects were all inpatients receiving oxygen administration and inpatients using respiratory ventilators, categorized by three age classes: all ages, patients 65 years old or older, and patients younger than 65 years old. We used logistic regression to analyze outcomes for underlying diseases, administered drugs, age, sex, the proportion of the mutated strains, and vaccine coverage.Results: Patients with hypertension, except for younger inpatients, have a lower risk of mortality (estimated coefficient 0.67 among all inpatients

Published
2023

35. Existing Data Sources for Clinical Epidemiology: Database of the National Hospital Organization in Japan

Author

Kanazawa,Natsuko, Tani,Takuaki, Imai,Shinobu, Horiguchi,Hiromasa, Fushimi,Kiyohide, and Inoue,Norihiko

Subjects
Clinical Epidemiology
Abstract

Natsuko Kanazawa,1,* Takuaki Tani,1,* Shinobu Imai,1– 3 Hiromasa Horiguchi,1 Kiyohide Fushimi,1,2 Norihiko Inoue1,2 1Department of Clinical Data Management and Research, Clinical Research Center, National Hospital Organization Headquarters, Tokyo, Japan; 2Department of Health Policy and Informatics, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan; 3Department of Drug Safety and Risk Management, School of Pharmacy, Tokyo University of Pharmacy and Life Sciences, Tokyo, Japan*These authors contributed equally to this workCorrespondence: Norihiko Inoue, Department of Clinical Data Management and Research, Clinical Research Center, National Hospital Organization Headquarters, 2-5-21 Higashigaoka, Meguroku, Tokyo, 152-8621, Japan, Tel +81-3-5712-5133, Fax +81-3-5712-5088, Email noricom.tmdu@gmail.comAbstract: This review introduces the National Hospital Organization (NHO) database in Japan. The NHO has maintained two databases through a system of data collection from 140 hospitals in the NHO. National Hospital Organization Clinical Data Archives (NCDA) is collecting clinical information in real time from the electronic medical records since January 2016, and Medical Information Analysis (MIA) databank is collecting daily insurance claims data since April 2010. The NHO database covers more than 8 million patients in 140 hospitals throughout Japan. The database consists of the information of patient profiles, hospital admission and discharge, diagnosis with ICD-10 codes, text data from medical chart, daily health insurance claims such as medical procedures, medications or surgeries, vital signs and laboratory data, and so on. The NHO database includes a wide variety of diseases and settings, including acute, chronic and intractable diseases, emergency medical services, disaster medicine, response to emerging infectious disease outbreaks, medical care according to health policies such as psychiatry, tuberculosis, or muscular dystrophy, and health systems in sparsely populated non-urban areas. Among several common diseases, the database has representativeness in terms of age distribution compared with the Patient Survey 2017 by the Ministry of Health, Labour and Welfare. Interested researchers can contact (700-dbproject@mail.hosp.go.jp) the NHO database division to obtain more information about the NHO database for utilization.Keywords: National Hospital Organization in Japan, real-world data, big data, diagnosis procedure combination, DPC, validation, database, linkage

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results