Akihiro Chiba

Akihiro Chiba

Auto-generated profile, based on publicly available information

Akihiro Chiba

NTT Corp, Tokyo, Japan

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 September 2022 in JMIR Bioinformatics and Biotechnology
Verified
Journal Article
Open access
HKHisashi Kurasawa
Hisashi Kurasawa
KWKayo Waki
Kayo Waki
ACAkihiro Chiba
Akihiro Chiba
TSTomohisa Seki
Tomohisa Seki
KHKatsuyoshi Hayashi
Katsuyoshi Hayashi
KOKazuhiko Ohe
Kazuhiko Ohe
Background: Treatment discontinuation (TD) is one of the major prognostic issues in diabetes care, and several models have been proposed to predict a missed appointment that may lead to TD in patients with diabetes by using binary classification models for the early detection of TD and for providing intervention support for patients. However, as binary classification models output the probability of a missed appointment occurring within a predetermined period, they are limited in their ability to estimate the magnitude of TD risk in patients with inconsistent intervals between appointments, making it difficult to prioritize patients for whom intervention support should be provided. Objective: This study aimed to develop a machine-learned prediction model that can output a TD risk score defined by the length of time until TD and prioritize patients for intervention according to their TD risk. Methods: This model included patients with diagnostic codes indicative of diabetes at the University of Tokyo Hospital between September 3, 2012, and May 17, 2014. The model was internally validated with patients from the same hospital from May 18, 2014, to January 29, 2016. The data used in this study included 7551 patients who visited the hospital after January 1, 2004, and had diagnostic codes indicative of diabetes. In particular, data that were recorded in the electronic medical records between September 3, 2012, and January 29, 2016, were used. The main outcome was the TD of a patient, which was defined as missing a scheduled clinical appointment and having no hospital visits within 3 times the average number of days between the visits of the patient and within 60 days. The TD risk score was calculated by using the parameters derived from the machine-learned ranking model. The prediction capacity was evaluated by using test data with the C-index for the performance of ranking patients, area under the receiver operating characteristic curve, and area under the precision-recall curve for discrimination, in addition to a calibration plot. Results: The means (95% confidence limits) of the C-index, area under the receiver operating characteristic curve, and area under the precision-recall curve for the TD risk score were 0.749 (0.655, 0.823), 0.758 (0.649, 0.857), and 0.713 (0.554, 0.841), respectively. The observed and predicted probabilities were correlated with the calibration plots. Conclusions: A TD risk score was developed for patients with diabetes by combining a machine-learned method with electronic medical records. The score calculation can be integrated into medical records to identify patients at high risk of TD, which would be useful in supporting diabetes care and preventing TD.

12 June 2014 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
ACAkihiro Chiba
Akihiro Chiba
TNTakaaki Nara
Takaaki Nara
This paper presents a novel method for the localization of a passive radio frequency identification (RFID) tag in a 2-D space. First, we show that the position of the tag can be estimated as the intersection of two orthogonal lines, which are determined by the weighted integrals of the magnetic flux density created by the tag. To measure them, we developed a square magnetic sensor composed of six coils: four rectangular coils, a set of four bow-tie-shaped coils connected in series, and a square coil. Using this sensor with side lengths of 200 mm, an RFID tag was localized in a 180 mm square domain with an average error of 5.1 mm. Using the sensor with side lengths of 400 mm, the RFID tag was also localized in a 300 mm square domain with an average error of 1.8 mm.

1 February 2020 in AIP Advances
Verified
Journal Article
Open access
PDF file
ACA. Chiba
A. Chiba
TNT. Nara
T. Nara
Indoor localization of objects when these bodies are affected by occlusion remains challenging. This paper presents a novel method to estimate the position of a magnetic marker that can be attached to objects such as a robot or a moving vehicle for indoor localization. We derive a formula to compute the azimuth and zenith angles of and the distance to a rotating magnet from the Fourier components of the magnetic flux density at the marker’s rotational frequency. The proposed method does not require temporal changes in the direction of the magnetic moment. As a result, the method does not require communication between the sensor and the marker. Also, using a Fourier component enhances the robustness of the method to environmental noise. The method is verified experimentally and shows an average error of 49.9 mm for estimation of the three-dimensional position of the marker in a 4000 mm by 2000 mm domain where z = 350 mm. In addition, we verified that the marker position can be estimated even if the sensor is tilted with respect to the horizontal plane using the sensor’s acceleration data.

18 July 2024 in JMIR AI
Verified
Journal Article
Open access
HKHisashi Kurasawa
Hisashi Kurasawa
KWKayo Waki
Kayo Waki
TSTomohisa Seki
Tomohisa Seki
ACAkihiro Chiba
Akihiro Chiba
AFAkinori Fujino
Akinori Fujino
KOKazuhiko Ohe
Kazuhiko Ohe
Background: Type 2 diabetes (T2D) is a significant global health challenge. Physicians need to assess whether future glycemic control will be poor on the current trajectory of usual care and usual-care treatment intensifications so that they can consider taking extra treatment measures to prevent poor outcomes. Predicting poor glycemic control from trends in hemoglobin A1c (HbA1c) levels is difficult due to the influence of seasonal fluctuations and other factors. Objective: We sought to develop a model that accurately predicts poor glycemic control among patients with T2D receiving usual care. Methods: Our machine learning model predicts poor glycemic control (HbA1c≥8%) using the transformer architecture, incorporating an attention mechanism to process irregularly spaced HbA1c time series and quantify temporal relationships of past HbA1c levels at each time point. We assessed the model using HbA1c levels from 7787 patients with T2D seeing specialist physicians at the University of Tokyo Hospital. The training data include instances of poor glycemic control occurring during usual care with usual-care treatment intensifications. We compared prediction accuracy, assessed with the area under the receiver operating characteristic curve, the area under the precision-recall curve, and the accuracy rate, to that of LightGBM. Results: The area under the receiver operating characteristic curve, the area under the precision-recall curve, and the accuracy rate (95% confidence limits) of the proposed model were 0.925 (95% CI 0.923-0.928), 0.864 (95% CI 0.852-0.875), and 0.864 (95% CI 0.86-0.869), respectively. The proposed model achieved high prediction accuracy comparable to or surpassing LightGBM’s performance. The model prioritized the most recent HbA1c levels for predictions. Older HbA1c levels in patients with poor glycemic control were slightly more influential in predictions compared to patients with good glycemic control. Conclusions: The proposed model accurately predicts poor glycemic control for patients with T2D receiving usual care, including patients receiving usual-care treatment intensifications, allowing physicians to identify cases warranting extraordinary treatment intensifications. If used by a nonspecialist, the model’s indication of likely future poor glycemic control may warrant a referral to a specialist. Future efforts could incorporate diverse and large-scale clinical data for improved accuracy.

29 June 2024 in Geriatrics & Gerontology International
Verified
Journal Article
Open access
ENEri Nakahara
Eri Nakahara
TIToshiko Iidaka
Toshiko Iidaka
ACAkihiro Chiba
Akihiro Chiba
HKHisashi Kurasawa
Hisashi Kurasawa
AFAkinori Fujino
Akinori Fujino
NYNoriko Yoshimura
Noriko Yoshimura
Aim: To identify factors associated with locomotive syndrome (LS) using medical questionnaire data and machine learning.Methods: A total of 1575 participants underwent the LS risk tests from the third survey of the research on osteoarthritis/osteoporosis against disability study (ROAD) study. LS was defined as stage 1 or higher based on clinical decision limits of the Japanese Orthopaedic Association. A total of 1335 items of medical questionnaire data came from this study. The number of medical questionnaire items was reduced from 1335 to 331 in data cleaning. From the 331 items, identify factors associated with LS use by light gradient boosting machine‐based recursive feature elimination with cross‐validation. The performance of each set was evaluated using an average of seven performance metrics, including 95% confidence intervals, using a bootstrapping method. The smallest set of items is determined with the highest average of receiver operating characteristic area under the curve (ROC‐AUC) under 20 items as association factors of LS. Additionally, the performance of the selected items was compared with the LS risk tests and Loco‐check.Results: The nine items have the best average ROC‐AUC under 20 items. The nine items show an average ROC‐AUC of 0.858 (95% confidence interval 0.816–0.898). Age and back pain during walking were strongly associated with the prevalence of LS. The ROC‐AUC of nine items is higher than that of existing questionnaire‐based LS assessments, including the 25‐question Geriatric Locomotor Scale and Loco‐check.Conclusions: The identified nine items could aid early LS detection, enhancing understanding and prevention. Geriatr Gerontol Int 2024; ••: ••–••.

1 January 2012 in Transactions of the Society of Instrument and Control Engineers
Verified
Journal Article
Closed access
ACAkihiro Chiba
Akihiro Chiba
TNTakaaki Nara
Takaaki Nara