Annals of clinical epidemiology最新文献

{"title":"Development and external validation of a deep learning-based computed tomography classification system for COVID-19.","authors":"Yuki Kataoka, Tomohisa Baba, Tatsuyoshi Ikenoue, Yoshinori Matsuoka, Junichi Matsumoto, Junji Kumasawa, Kentaro Tochitani, Hiraku Funakoshi, Tomohiro Hosoda, Aiko Kugimiya, Michinori Shirano, Fumiko Hamabe, Sachiyo Iwata, Yoshiro Kitamura, Tsubasa Goto, Shingo Hamaguchi, Takafumi Haraguchi, Shungo Yamamoto, Hiromitsu Sumikawa, Koji Nishida, Haruka Nishida, Koichi Ariyoshi, Hiroaki Sugiura, Hidenori Nakagawa, Tomohiro Asaoka, Naofumi Yoshida, Rentaro Oda, Takashi Koyama, Yui Iwai, Yoshihiro Miyashita, Koya Okazaki, Kiminobu Tanizawa, Tomohiro Handa, Shoji Kido, Shingo Fukuma, Noriyuki Tomiyama, Toyohiro Hirai, Takashi Ogura","doi":"10.37737/ace.22014","DOIUrl":"https://doi.org/10.37737/ace.22014","url":null,"abstract":"<p><strong>Background: </strong>We aimed to develop and externally validate a novel machine learning model that can classify CT image findings as positive or negative for SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR).</p><p><strong>Methods: </strong>We used 2,928 images from a wide variety of case-control type data sources for the development and internal validation of the machine learning model. A total of 633 COVID-19 cases and 2,295 non-COVID-19 cases were included in the study. We randomly divided cases into training and tuning sets at a ratio of 8:2. For external validation, we used 893 images from 740 consecutive patients at 11 acute care hospitals suspected of having COVID-19 at the time of diagnosis. The dataset included 343 COVID-19 patients. The reference standard was RT-PCR.</p><p><strong>Results: </strong>In external validation, the sensitivity and specificity of the model were 0.869 and 0.432, at the low-level cutoff, 0.724 and 0.721, at the high-level cutoff. Area under the receiver operating characteristic was 0.76.</p><p><strong>Conclusions: </strong>Our machine learning model exhibited a high sensitivity in external validation datasets and may assist physicians to rule out COVID-19 diagnosis in a timely manner at emergency departments. Further studies are warranted to improve model specificity.</p>","PeriodicalId":517436,"journal":{"name":"Annals of clinical epidemiology","volume":"4 4","pages":"110-119"},"PeriodicalIF":0.0,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760489/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140178640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Accuracy of Japanese Administrative Data in Identifying Acute Exacerbation of Idiopathic Pulmonary Fibrosis.","authors":"Keisuke Anan, Yuki Kataoka, Kazuya Ichikado, Kodai Kawamura, Takeshi Johkoh, Kiminori Fujimoto, Kazunori Tobino, Ryo Tachikawa, Hiroyuki Ito, Takahito Nakamura, Tomoo Kishaba, Minoru Inomata, Yosuke Yamamoto","doi":"10.37737/ace.22008","DOIUrl":"https://doi.org/10.37737/ace.22008","url":null,"abstract":"<p><strong>Background: </strong>This study aimed to develop criteria for identifying patients with acute exacerbation of idiopathic pulmonary fibrosis (AE-IPF) from Japanese administrative data and validate the pre-existing criteria.</p><p><strong>Methods: </strong>This retrospective, multi-center validation study was conducted at eight institutes in Japan to verify the diagnostic accuracy of the disease name for AE-IPF. We used the Japanese Diagnosis Procedure Combination data to identify patients with a disease name that could meet the diagnostic criteria for AE-IPF, who were admitted to the eight institutes from January 2016 to February 2019. As a reference standard, two respiratory physicians performed a chart review to determine whether the patients had a disease that met the diagnostic criteria for AE-IPF. Furthermore, two radiologists interpreted the chest computed tomography findings of cases considered AE-IPF and confirmed the diagnosis. We calculated the positive predictive value (PPV) for each disease name and its combination.</p><p><strong>Results: </strong>We included 830 patients; among them, 216 were diagnosed with AE-IPF through the chart review. We combined the groups of disease names and yielded two criteria: the criteria with a high PPV (0.72 [95% confidence interval 0.62 to 0.81]) and that with a slightly less PPV (0.61 [0.53 to 0.68]) but more true positives. Pre-existing criteria showed a PPV of 0.40 (0.31 to 0.49).</p><p><strong>Conclusion: </strong>The criteria derived in this study for identifying AE-IPF from Japanese administrative data show a fair PPV. Although these criteria should be carefully interpreted according to the target population, our findings could be utilized in future database studies on AE-IPF.</p>","PeriodicalId":517436,"journal":{"name":"Annals of clinical epidemiology","volume":"4 2","pages":"53-62"},"PeriodicalIF":0.0,"publicationDate":"2022-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760466/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140178639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introduction to Regression Discontinuity Design.","authors":"Yusuke Sasabuchi","doi":"10.37737/ace.22001","DOIUrl":"https://doi.org/10.37737/ace.22001","url":null,"abstract":"<p><p>It is common clinical practice for physicians to refer to specific diagnostic criteria for day-to-day decision-making. In particular, whether or not to provide a particular treatment is often determined by the cutoff value of a relevant diagnostic marker. Regression discontinuity design (RDD) is a method for evaluating scenarios where intervention is determined by the certain cutoff value (e.g., threshold) of a continuous variable. RDD represents a powerful method for assessing intervention effects and outcomes. RDD is underutilized in clinical research and there are many opportunities to apply RDD in this setting. This article introduces the principles of RDD and provides examples of clinical studies that have used this design.</p>","PeriodicalId":517436,"journal":{"name":"Annals of clinical epidemiology","volume":"4 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760478/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140178636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prescription and Therapeutic Drug Monitoring Status of Valproic Acid among Patients Receiving Carbapenem Antibiotics: A Preliminary Survey Using a Japanese Claims Database.","authors":"Shungo Imai, Kenji Momo, Hitoshi Kashiwagi, Yuki Sato, Takayuki Miyai, Mitsuru Sugawara, Yoh Takekuma","doi":"10.37737/ace.22002","DOIUrl":"https://doi.org/10.37737/ace.22002","url":null,"abstract":"","PeriodicalId":517436,"journal":{"name":"Annals of clinical epidemiology","volume":"4 1","pages":"6-10"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760476/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140178637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Factors Associated with Outpatient Cardiac Rehabilitation Participation in Older Patients: A Population-Based Study Using Claims Data from Two Cities in Japan.","authors":"Jun Komiyama, Masao Iwagami, Takahiro Mori, Naoaki Kuroda, Xueying Jin, Tomoko Ito, Nanako Tamiya","doi":"10.37737/ace.22003","DOIUrl":"https://doi.org/10.37737/ace.22003","url":null,"abstract":"<p><strong>Background: </strong>Although outpatient cardiac rehabilitation has been shown to be effective, the participation status of older cardiac patients is unclear in real-world settings. We investigated the proportion and associated factors of outpatient cardiac rehabilitation participation among older patients with heart diseases after cardiac intervention.</p><p><strong>Methods: </strong>We analyzed data from medical and long-term care insurance claims data from two municipalities in Japan. The data coverage period was between April 2014 and March 2019 in City A and between April 2012 and November 2016 in City B. We identified patients aged ≥65 years with post-operative acute myocardial infarction, angina pectoris, or heart valve disease. We estimated the proportion of cardiac rehabilitation participation and conducted logistic regression to identify factors (age, sex, type of cardiac disease, open-heart surgery, Charlson comorbidity index, long-term care need level, catecholamine use, inpatient cardiac rehabilitation, and hospital volume for cardiac rehabilitation) associated with outpatient cardiac rehabilitation participation.</p><p><strong>Results: </strong>A total of 690 patients were included in this study. The proportion of patients receiving outpatient cardiac rehabilitation was 9.0% overall. Multivariable logistic regression analysis suggested that men (adjusted OR 3.98; 95% CI 1.69-9.37), acute myocardial infarction (adjusted OR 2.76; 95% CI 1.20-6.36; reference angina pectoris), inpatient cardiac rehabilitation (adjusted OR 17.01; 95% CI 5.33-54.24), and \"hospital volume\" for cardiac rehabilitation (adjusted OR 4.35; 95% CI 1.14-16.57 for high-volume hospitals; reference low-volume hospital) were independently associated with outpatient cardiac rehabilitation.</p><p><strong>Conclusions: </strong>The participation rate of outpatient cardiac rehabilitation among older post-operative cardiac patients was suboptimal. Further studies are warranted to examine its generalizability and whether a targeted approach to a group of patients who are less likely to receive outpatient cardiac rehabilitation could improve the participation rate.</p>","PeriodicalId":517436,"journal":{"name":"Annals of clinical epidemiology","volume":"4 1","pages":"11-19"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760477/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140178635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validation Study of Algorithms to Identify Malignant Tumors and Serious Infections in a Japanese Administrative Healthcare Database.","authors":"Atsushi Nishikawa, Eiko Yoshinaga, Masaki Nakamura, Masayoshi Suzuki, Keiji Kido, Naoto Tsujimoto, Taeko Ishii, Daisuke Koide","doi":"10.37737/ace.22004","DOIUrl":"https://doi.org/10.37737/ace.22004","url":null,"abstract":"<p><strong>Background: </strong>This retrospective observational study validated case-finding algorithms for malignant tumors and serious infections in a Japanese administrative healthcare database.</p><p><strong>Methods: </strong>Random samples of possible cases of each disease (January 2015-January 2018) from two hospitals participating in the Medical Data Vision Co., Ltd. (MDV) database were identified using combinations of ICD-10 diagnostic codes and other procedural/billing codes. For each disease, two physicians identified true cases among the random samples of possible cases by medical record review; a third physician made the final decision in cases where the two physicians disagreed. The accuracy of case-finding algorithms was assessed using positive predictive value (PPV) and sensitivity.</p><p><strong>Results: </strong>There were 2,940 possible cases of malignant tumor; 180 were randomly selected and 108 were identified as true cases after medical record review. One case-finding algorithm gave a high PPV (64.1%) without substantial loss in sensitivity (90.7%) and included ICD-10 codes for malignancy and photographing/imaging. There were 3,559 possible cases of serious infection; 200 were randomly selected and 167 were identified as true cases after medical record review. Two case-finding algorithms gave a high PPV (85.6%) with no loss in sensitivity (100%). Both case-finding algorithms included the relevant diagnostic code and immunological infection test/other related test and, of these, one also included pathological diagnosis within 1 month of hospitalization.</p><p><strong>Conclusions: </strong>The case-finding algorithms in this study showed good PPV and sensitivity for identification of cases of malignant tumors and serious infections from an administrative healthcare database in Japan.</p>","PeriodicalId":517436,"journal":{"name":"Annals of clinical epidemiology","volume":"4 1","pages":"20-31"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760479/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140178638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}