Faculty Profiles - FUJIHARA Kazuya

Papers - FUJIHARA Kazuya

Division display 141 - 160 of about 320 ／ All the affair displays >>

心血管疾患既往の有無と耐糖能状態別に見たその後の心血管疾患発症リスク

北澤勝, 藤原和哉, 山田万祐子, 大澤妙子, 矢口雄大, 山本正彦, 金子正儀, 松林泰弘, 山田貴穂, 清田浩康, 曽根博仁

日本内分泌学会雑誌 97 ( 1 ) 274 - 274 2021.4

ソマトスタチン受容体シンチグラフィが診断に有用であった肺カルチノイドによる周期性ACTH依存性クッシング症候群の1例

金子正儀, 佐藤隆明, 福武嶺一, 滝澤祥子, 今西明, 安楽匠, 小松健, 北澤勝, 松林泰弘, 岩永みどり, 山田貴穂, 藤原和哉, 曽根博仁

日本内分泌学会雑誌 97 ( 1 ) 363 - 363 2021.4

ソマトスタチン受容体シンチグラフィが診断に有用であった肺カルチノイドによる周期性ACTH依存性クッシング症候群の1例

金子正儀, 佐藤隆明, 福武嶺一, 滝澤祥子, 今西明, 安楽匠, 小松健, 北澤勝, 松林泰弘, 岩永みどり, 山田貴穂, 藤原和哉, 曽根博仁

日本内分泌学会雑誌 97 ( 1 ) 363 - 363 2021.4

心血管疾患既往の有無と耐糖能状態別に見たその後の心血管疾患発症リスク

北澤勝, 藤原和哉, 山田万祐子, 大澤妙子, 矢口雄大, 山本正彦, 金子正儀, 松林泰弘, 山田貴穂, 清田浩康, 曽根博仁

日本内分泌学会雑誌 97 ( 1 ) 274 - 274 2021.4

Association of estimated plasma volume and weight loss after long-term administration and subsequent discontinuation of the SGLT2 inhibitor, tofogliflozin. International journal

Yasuhiro Matsubayashi, Akihiro Yoshida, Hideki Suganami, Momoko Oe, Takaaki Sato, Yuta Yaguchi, Kazuya Fujihara, Takaho Yamada, Shiro Tanaka, Kohei Kaku, Hirohito Sone

Diabetes, obesity & metabolism 23 ( 7 ) 1660 - 1665 2021.3

Language：English Publishing type：Research paper (scientific journal)

Sodium/glucose-cotransporter 2 inhibitors (SGLT2is) are drugs that have been reported to have several effects through the regulation of plasma volume such as antihypertensive effects, etc. This study aimed to clarify the impact of long-term administration and subsequent discontinuation of the SGLT2i tofogliflozin on estimated plasma volume (ePV), brain natriuretic peptide (BNP) and the relationship between changes in ePV, BNP and body weight (BW). Data from 157 participants with type 2 diabetes receiving tofogliflozin monotherapy in a phase 3 study were analyzed. Changes in variables or correlations among them during a 52-week administration and 2-week post-treatment period were investigated. Percent change in ePV was calculated by the Strauss Formula. Significant decreases in BW, ePV and ln-transformed BNP (ln-BNP) were noted by week 52. %ΔBW was not significantly correlated with %ΔePV and Δln-BNP while %ΔePV was significantly correlated with Δln-BNP. Two weeks after discontinuation of tofogliflozin, BW, ePV and ln-BNP were significantly increased. %ΔBW was significantly correlated with %ΔePV and Δln-BNP. Furthermore, ePV and BNP were significantly higher than baseline levels. This article is protected by copyright. All rights reserved.

DOI： 10.1111/dom.14387

PubMed

researchmap

Author Correction: Meta-analytic research of the dose-response relationship between salt intake and risk of heart failure. International journal

Satoru Kodama, Chika Horikawa, Kazuya Fujihara, Mariko Hatta, Yasunaga Takeda, Rena Nedachi, Kiminori Kato, Kenichi Watanabe, Hirohito Sone

Hypertension research : official journal of the Japanese Society of Hypertension 44 ( 7 ) 894 - 894 2021.3

The DPP-4 inhibitor, anagliptin, alters hepatic insulin clearance in relation to the glycemic status in Japanese individuals with type 2 diabetes.

Takahiro Abe, Yasuhiro Matsubayashi, Sayaka Muragishi, Akihiro Yoshida, Hideki Suganami, Kenichi Furusawa, Kazuya Fujihara, Shiro Tanaka, Kohei Kaku, Hirohito Sone

Journal of diabetes investigation 12 ( 10 ) 1805 - 1815 2021.3

Language：English Publishing type：Research paper (scientific journal)

AIMS/INTRODUCTION: This study investigated the impact of the DPP-4 inhibitor, anagliptin, on hepatic insulin clearance (HIC) in Japanese type 2 diabetes patients and explored its relation to glycemic status. MATERIALS AND METHODS: Data on 765 participants in anagliptin phase 2 and 3 studies were analyzed. Adjusted changes in variables during 12 weeks of anagliptin therapy were compared with placebo. HIC was calculated as the ratio, c-peptide area under the curve (AUC)0-120min to insulin AUC0-120min, after a meal tolerance test. To explore the effects of baseline HIC levels on variables, participants receiving anagliptin were divided according to quartiles of baseline HIC. Further, multivariate analysis investigated the association between baseline HIC levels and glycemic status. RESULTS: Anagliptin significantly reduced HbA1c levels (p<0.001 vs. placebo) and HIC levels (p<0.01). Longer duration of diabetes, lower BMI, higher HbA1c and lower insulin secretion capacity were observed with increases in baseline HIC levels. Improvements in HbA1c, glycoalbumin and 1,5-anhydroglucitol levels were greater in the relatively higher HIC group (baseline HIC levels ≥ median) than in the lower HIC group (<median). CONCLUSIONS: Anagliptin affected HIC levels according to HIC baseline levels. Higher baseline HIC values may result in improved hyperglycemia through reduced HIC.

DOI： 10.1111/jdi.13543

PubMed

researchmap

Meta-analytic research of the dose-response relationship between salt intake and risk of heart failure. International journal

Satoru Kodama, Chika Horikawa, Kazuya Fujihara, Mariko Hatta, Yasunaga Takeda, Rena Nedachi, Kiminori Kato, Kenichi Watanabe, Hirohito Sone

Hypertension research : official journal of the Japanese Society of Hypertension 44 ( 7 ) 885 - 887 2021.3

Body flexibility and incident hypertension: The Niigata wellness study. International journal

Yuko Gando, Susumu S Sawada, Haruki Momma, Ryoko Kawakami, Motohiko Miyachi, I-Min Lee, Steven N Blair, Minoru Tashiro, Chika Horikawa, Yasuhiro Matsubayashi, Takaho Yamada, Kazuya Fujihara, Kiminori Kato, Hirohito Sone

Scandinavian journal of medicine & science in sports 31 ( 3 ) 702 - 709 2021.3

Language：English Publishing type：Research paper (scientific journal)

A high level of physical fitness, especially cardiorespiratory fitness, is associated with lower incidence of hypertension. However, the relationship between flexibility, which is a component of physical fitness, and the incidence of hypertension is unknown. The purpose of this study was to investigate the relationship between flexibility and the incidence of hypertension in a cohort study. A total of 22,972 (14,805 men and 8167 women; median age 49 years) normotensive participants were included in this study. Between April 2001 and March 2002, flexibility (standing forward bending) was measured using a standing trunk flexion meter. The participants were divided into quartiles of flexibility by sex and age group. Hypertension was defined as systolic blood pressure ≥ 140 mm Hg, diastolic blood pressure ≥ 90 mm Hg, or a self-reported history of previously diagnosed hypertension or current medication for hypertension at a health examination between April 2002 and March 2008. Hazard ratios and 95% confidence intervals (95% CI) for the incidence of hypertension were estimated using Cox proportional hazards models after adjusting for age, sex, body mass index, exercise habits, smoking status, and drinking status. During 102,948 person years of follow-up (median 5.6 years), 4235 participants developed hypertension. Compared with the lowest flexibility (quartile 1), hazard ratios and 95% CI were 0.96 (0.88 - 1.04) for quartile 2, 0.94 (0.86 - 1.03) for quartile 3, and 0.83 (0.76 - 0.91) for quartile 4. A high level of flexibility was associated with lower incidence of hypertension, independent of other confounding factors.

DOI： 10.1111/sms.13867

PubMed

researchmap

Severity of hypertension as a predictor of initiation of dialysis among study participants with and without diabetes mellitus. International journal

Taeko Osawa, Kazuya Fujihara, Mayuko Harada Yamada, Masahiko Yamamoto, Masaru Kitazawa, Yasuhiro Matsubayashi, Midori Iwanaga, Takaho Yamada, Hiroyasu Seida, Satoru Kodama, Yoshimi Nakagawa, Hitoshi Shimano, Hirohito Sone

Journal of investigative medicine : the official publication of the American Federation for Clinical Research 69 ( 3 ) 724 - 729 2021.3

Language：English Publishing type：Research paper (scientific journal)

To determine associations between severity of hypertension and risk of starting dialysis in the presence or absence of diabetes mellitus (DM). A nationwide database with claims data on 258 874 people with and without DM aged 19-72 years in Japan was used to elucidate the impact of severity of hypertension on starting dialysis. Initiation of dialysis was determined from claims using International Classification of Diseases-10 codes and medical procedures. Using multivariate Cox modeling, we investigated the severity of hypertension to predict the initiation of dialysis with and without DM. Hypertension was significantly associated with the initiation of dialysis regardless of DM. The incidence of starting dialysis in those with systolic blood pressure (SBP) ≤119 mm Hg and DM (DM+) was almost the same as in those with SBP ≥150 mm Hg and absence of DM (DM-). In comparison with SBP ≤119 mm Hg, SBP ≥150 mm Hg significantly increased the risk of the initiation of dialysis about 2.5 times regardless of DM+ or DM-. Compared with DM- and SBP ≤119 mm Hg, the HR for DM+ and SBP ≥150 mm Hg was 6.88 (95% CI 3.66 to 12.9). Although the risks of hypertension differed only slightly regardless of the presence or absence of DM, risks for starting dialysis with DM+ and SBP ≤119 mm Hg were equivalent to DM- and SBP ≥150 mm Hg, indicating more strict blood pressure interventions in DM+ are needed to avoid dialysis. Future studies are required to clarify the cut-off SBP level to avoid initiation of dialysis considering the risks of strict control of blood pressure.

DOI： 10.1136/jim-2020-001489

PubMed

researchmap

A 52-week randomized controlled trial of ipragliflozin or sitagliptin in type 2 diabetes combined with metformin: The N-ISM study. International journal

Masaru Kitazawa, Takashi Katagiri, Hiromi Suzuki, Satoshi Matsunaga, Mayuko H Yamada, Tomoo Ikarashi, Masahiko Yamamoto, Kazuo Furukawa, Midori Iwanaga, Mariko Hatta, Kazuya Fujihara, Takaho Yamada, Shiro Tanaka, Hirohito Sone

Diabetes, obesity & metabolism 23 ( 3 ) 811 - 821 2021.3

Language：English Publishing type：Research paper (scientific journal)

AIM: To compare the long-term efficacy of sodium-glucose co-transporter-2 inhibitors and dipeptidyl peptidase-4 inhibitors as second-line drugs after metformin for patients not at high risk of atherosclerotic cardiovascular disease (ASCVD). MATERIALS AND METHODS: In a 52-week randomized open-label trial, we compared ipragliflozin and sitagliptin in Japanese patients diagnosed with type 2 diabetes, without prior ASCVD and treated with metformin. The primary endpoint was a glycated haemoglobin (HbA1c) reduction of ≥0.5% (5.5 mmol/mol) without weight gain at 52 weeks. RESULTS: Of a total of 111 patients (mean age 59.2 years, mean body mass index [BMI] 26.6 kg/m2 , 61.3% men), 54 patients received ipragliflozin and 57 received sitagliptin. After 52 weeks, achievement of the primary endpoint was not significantly different (37.0% and 40.3%; P = 0.72). HbA1c reduction rate at 24 weeks was greater for sitagliptin (56.1%) than for ipragliflozin (31.5%; P = 0.01). From 24 to 52 weeks, the HbA1c reduction with sitagliptin was attenuated, with no significant difference in HbA1c reduction after 52 weeks between sitagliptin (54.4%) and ipragliflozin (38.9%; P = 0.10). Improvements in BMI, C-peptide and high-density lipoprotein cholesterol were greater with ipragliflozin than with sitagliptin. Adverse events occurred in 17 patients with ipragliflozin and in 10 patients with sitagliptin (P = 0.11). CONCLUSION: The HbA1c-lowering effect at 24 weeks was greater with sitagliptin than with ipragliflozin, but with no difference in efficacy related to HbA1c and body weight at 52 weeks. However, some ASCVD risk factors improved with ipragliflozin.

DOI： 10.1111/dom.14288

PubMed

researchmap

特定保健指導の最適介入法の同定を目指した前向き研究新潟方式の試作とそのパイロットスタディによる効果の評価

加藤公則, 田代稔, 鈴木沙織, 大塚政人, 小林隆司, 三木扶久子, 春木匠, 小松原祐介, 藤原和哉, 津下一代, 赤澤宏平, 曽根博仁

人間ドック 35 ( 5 ) 704 - 712 2021.3

Language：Japanese Publisher：(公社)日本人間ドック学会

目的:2018年度より特定健診・特定保健指導も第3期を迎え、「柔軟な運用による特定保健指導のモデル実施(以下モデル実施と略す)」が設けられた。このモデル実施を用いた新たな特定保健指導「新潟方式」を確立するために、現状の保健指導180ポイントにおいて、その効果に有効下限閾値があるのかを検証した。方法:対象は、2018年4月から12月までに特定健診を受けた人で、特定保健指導の積極的支援の対象者202人、A群0ポイント、B群20ポイント、C群100ポイント、D群180ポイントの4群に分け、保健指導終了の3ヵ月後の実績評価時に、腹囲2.0cm以上かつ体重2.0kg以上相当に減少した者(達成者)の割合を群間比較し、有効下限閾値の有無を検討した。また翌年の特定健診データとも比較検討し、その特定保健指導効果の持続性も確認した。結果:実績評価時の達成者の割合については、A群20.4%、B群36.0%、C群28.0%、D群12.5%であり、BとD群間のみ有意差が認められた。実績評価時の達成者が翌年も達成者のままでいた人はA群80.0%、B群88.9%、C群92.3%、D群100%であり、群間に有意差はなかった。結論:実績評価時において、保健指導の効果にはポイント数に依存する関係は存在せず、有効下限閾値は存在しなかった。また、翌年も特定保健指導の効果が持続していた。(著者抄録)

researchmap

特定保健指導の最適介入法の同定を目指した前向き研究新潟方式の試作とそのパイロットスタディによる効果の評価

加藤公則, 田代稔, 鈴木沙織, 大塚政人, 小林隆司, 三木扶久子, 春木匠, 小松原祐介, 藤原和哉, 津下一代, 赤澤宏平, 曽根博仁

人間ドック 35 ( 5 ) 704 - 712 2021.3

Language：Japanese Publisher：(公社)日本人間ドック学会

researchmap

Sodium Intake and Incidence of Diabetes Complications in Elderly Patients with Type 2 Diabetes-Analysis of Data from the Japanese Elderly Diabetes Intervention Study (J-EDIT). International journal

Chika Horikawa, Rei Aida, Shiro Tanaka, Chiemi Kamada, Sachiko Tanaka, Yukio Yoshimura, Remi Kodera, Kazuya Fujihara, Ryo Kawasaki, Tatsumi Moriya, Hidetoshi Yamashita, Hideki Ito, Hirohito Sone, Atsushi Araki

Nutrients 13 ( 2 ) 2021.2

Language：English Publishing type：Research paper (scientific journal)

This study investigates the associations between sodium intake and diabetes complications in a nationwide cohort of elderly Japanese patients with type 2 diabetes aged 65-85. Data from 912 individuals regarding their dietary intake at baseline is analyzed and assessed by the Food Frequency Questionnaire based on food groups. Primary outcomes are times to diabetic retinopathy, overt nephropathy, cardiovascular disease (CVD), and all-cause mortality during six years. We find that mean sodium intake in quartiles ranges from 2.5 g to 5.9 g/day. After adjustment for confounders, no significant associations are observed between sodium intake quartiles and incidence of diabetes complications and mortality, except for a significant trend for an increased risk of diabetic retinopathy (p = 0.039). Among patients whose vegetable intake was less than the average of 268.7 g, hazard ratios (HRs) for diabetic retinopathy in patients in the second, third, and fourth quartiles of sodium intake compared with the first quartile were 0.87 (95% CI, 0.31-2.41), 2.61 (1.00-6.83), and 3.70 (1.37-10.02), respectively. Findings indicate that high sodium intake under conditions of low vegetable intake is associated with an elevated incidence of diabetic retinopathy in elderly patients with type 2 diabetes.

DOI： 10.3390/nu13020689

PubMed

researchmap

A Prospective Cohort Study of Muscular and Performance Fitness and Risk of Hearing Loss: The Niigata Wellness Study. Reviewed International journal

Ryoko Kawakami, Susumu S Sawada, Kiminori Kato, Yuko Gando, Haruki Momma, Hideaki Oike, Motohiko Miyachi, I-Min Lee, Steven N Blair, Minoru Tashiro, Chika Horikawa, Yasuhiro Matsubayashi, Takaho Yamada, Kazuya Fujihara, Hirohito Sone

The American journal of medicine 134 ( 2 ) 235 - 242 2021.2

Language：English Publishing type：Research paper (scientific journal)

BACKGROUND: Several cross-sectional studies have linked higher physical fitness with better hearing sensitivity but have not established a causal relation; none have used a prospective design that is less susceptible to bias. We used a prospective cohort study to investigate the association between muscular and performance fitness and the incidence of hearing loss. METHODS: A total of 21,907 participants without hearing loss received physical fitness assessments between April 2001 and March 2002. Muscular and performance fitness index, an age- and sex-specific summed z-score based on grip strength, vertical jump height, single-leg balance, forward bending, and whole-body reaction time was calculated. Participants were classified into quartiles according to the muscular and performance fitness index and each physical fitness test. They were followed up for the development of hearing loss, assessed by pure-tone audiometry at annual health examinations between April 2002 and March 2008. Hazard ratios and 95% confidence intervals for hearing loss incidence were estimated using Cox proportional hazards regression models. RESULTS: During follow-up, 2765 participants developed hearing loss. The hazard ratios (95% confidence intervals) for developing hearing loss across the muscular and performance fitness index quartiles (lowest to highest) were 1.00 (reference), 0.88 (0.79-0.97), 0.83 (0.75-0.93), and 0.79 (0.71-0.88) (Ptrend <.001). Among the various physical fitness components, a clear dose-response association with hearing loss incidence was observed for vertical jump height and single-leg balance (Ptrend <.001 for both). CONCLUSION: Higher muscular and performance fitness is associated with a lower incidence of hearing loss.

DOI： 10.1016/j.amjmed.2020.06.021

PubMed

researchmap

糖尿病患者におけるIoT端末による食事運動記録と持続血糖測定器を用いた新しい食事運動療法の開発

北澤勝, 藤原和哉, 石澤正博, 松林泰弘, 山田貴穂, 曽根博仁

新潟県医師会報 ( 851 ) 10 - 11 2021.2

メタ解析的アプローチによる塩分摂取と心不全発症リスクとの量-反応分析

児玉暁, 藤原和哉, 渡辺賢一, 加藤公則, 曽根博仁

日本内科学会雑誌 110 ( Suppl. ) 142 - 142 2021.2

Ability of Current Machine Learning Algorithms to Predict and Detect Hypoglycemia in Patients With Diabetes Mellitus: Meta-analysis. International journal

Satoru Kodama, Kazuya Fujihara, Haruka Shiozaki, Chika Horikawa, Mayuko Harada Yamada, Takaaki Sato, Yuta Yaguchi, Masahiko Yamamoto, Masaru Kitazawa, Midori Iwanaga, Yasuhiro Matsubayashi, Hirohito Sone

JMIR diabetes 6 ( 1 ) e22458 2021.1

Language：English Publishing type：Research paper (scientific journal)

BACKGROUND: Machine learning (ML) algorithms have been widely introduced to diabetes research including those for the identification of hypoglycemia. OBJECTIVE: The objective of this meta-analysis is to assess the current ability of ML algorithms to detect hypoglycemia (ie, alert to hypoglycemia coinciding with its symptoms) or predict hypoglycemia (ie, alert to hypoglycemia before its symptoms have occurred). METHODS: Electronic literature searches (from January 1, 1950, to September 14, 2020) were conducted using the Dialog platform that covers 96 databases of peer-reviewed literature. Included studies had to train the ML algorithm in order to build a model to detect or predict hypoglycemia and test its performance. The set of 2 × 2 data (ie, number of true positives, false positives, true negatives, and false negatives) was pooled with a hierarchical summary receiver operating characteristic model. RESULTS: A total of 33 studies (14 studies for detecting hypoglycemia and 19 studies for predicting hypoglycemia) were eligible. For detection of hypoglycemia, pooled estimates (95% CI) of sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) were 0.79 (0.75-0.83), 0.80 (0.64-0.91), 8.05 (4.79-13.51), and 0.18 (0.12-0.27), respectively. For prediction of hypoglycemia, pooled estimates (95% CI) were 0.80 (0.72-0.86) for sensitivity, 0.92 (0.87-0.96) for specificity, 10.42 (5.82-18.65) for PLR, and 0.22 (0.15-0.31) for NLR. CONCLUSIONS: Current ML algorithms have insufficient ability to detect ongoing hypoglycemia and considerate ability to predict impeding hypoglycemia in patients with diabetes mellitus using hypoglycemic drugs with regard to diagnostic tests in accordance with the Users' Guide to Medical Literature (PLR should be ≥5 and NLR should be ≤0.2 for moderate reliability). However, it should be emphasized that the clinical applicability of these ML algorithms should be evaluated according to patients' risk profiles such as for hypoglycemia and its associated complications (eg, arrhythmia, neuroglycopenia) as well as the average ability of the ML algorithms. Continued research is required to develop more accurate ML algorithms than those that currently exist and to enhance the feasibility of applying ML in clinical settings. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD42020163682; http://www.crd.york.ac.uk/PROSPERO/display_record.php?ID=CRD42020163682.

DOI： 10.2196/22458

PubMed

researchmap

Machine Learning Approach to Decision Making for Insulin Initiation in Japanese Patients With Type 2 Diabetes (JDDM 58): Model Development and Validation Study. International journal

Kazuya Fujihara, Yasuhiro Matsubayashi, Mayuko Harada Yamada, Masahiko Yamamoto, Toshihiro Iizuka, Kosuke Miyamura, Yoshinori Hasegawa, Hiroshi Maegawa, Satoru Kodama, Tatsuya Yamazaki, Hirohito Sone

JMIR medical informatics 9 ( 1 ) e22148 2021.1

Language：English Publishing type：Research paper (scientific journal)

BACKGROUND: Applications of machine learning for the early detection of diseases for which a clear-cut diagnostic gold standard exists have been evaluated. However, little is known about the usefulness of machine learning approaches in the decision-making process for decisions such as insulin initiation by diabetes specialists for which no absolute standards exist in clinical settings. OBJECTIVE: The objectives of this study were to examine the ability of machine learning models to predict insulin initiation by specialists and whether the machine learning approach could support decision making by general physicians for insulin initiation in patients with type 2 diabetes. METHODS: Data from patients prescribed hypoglycemic agents from December 2009 to March 2015 were extracted from diabetes specialists' registries, resulting in a sample size of 4860 patients who had received initial monotherapy with either insulin (n=293) or noninsulin (n=4567). Neural network output was insulin initiation ranging from 0 to 1 with a cutoff of >0.5 for the dichotomous classification. Accuracy, recall, and area under the receiver operating characteristic curve (AUC) were calculated to compare the ability of machine learning models to make decisions regarding insulin initiation to the decision-making ability of logistic regression and general physicians. By comparing the decision-making ability of machine learning and logistic regression to that of general physicians, 7 cases were chosen based on patient information as the gold standard based on the agreement of 8 of the 9 specialists. RESULTS: The AUCs, accuracy, and recall of logistic regression were higher than those of machine learning (AUCs of 0.89-0.90 for logistic regression versus 0.67-0.74 for machine learning). When the examination was limited to cases receiving insulin, discrimination by machine learning was similar to that of logistic regression analysis (recall of 0.05-0.68 for logistic regression versus 0.11-0.52 for machine learning). Accuracies of logistic regression, a machine learning model (downsampling ratio of 1:8), and general physicians were 0.80, 0.70, and 0.66, respectively, for 43 randomly selected cases. For the 7 gold standard cases, the accuracies of logistic regression and the machine learning model were 1.00 and 0.86, respectively, with a downsampling ratio of 1:8, which were higher than the accuracy of general physicians (ie, 0.43). CONCLUSIONS: Although we found no superior performance of machine learning over logistic regression, machine learning had higher accuracy in prediction of insulin initiation than general physicians, defined by diabetes specialists' choice of the gold standard. Further study is needed before the use of machine learning-based decision support systems for insulin initiation can be incorporated into clinical practice.

DOI： 10.2196/22148

PubMed

researchmap

糖尿病と定期的な運動習慣が要介護発症へ及ぼす影響の検討

藤原和哉, 山田万祐子, 北澤勝, 松林泰弘, 八尋拓也, 筒井歩, 加藤公則, 曽根博仁

Journal of Epidemiology 31 ( Suppl. ) 102 - 102 2021.1

　 PREV - NEXT 　

<FUJIHARA Kazuya>

Papers - FUJIHARA Kazuya