AKAkifumi Kishi

Akifumi Kishi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Akifumi Kishi has a total of 56 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Sleep Staging Using PPG-Derived Heart Rate and Accelerometer Data From a Smart Ring With Lightweight Neural Networks

    by Roneel V. Sharan, Hiroki Takeuchi, Akifumi Kishi, Jiabin Wang, Tatsuhiko Watanabe, Yoshiharu Yamamoto

    Sleep staging plays an important role in assessing and diagnosing sleep disorders, however, polysomnography, the gold standard for sleep monitoring, is expensive, time-consuming, and often inaccessible. Wearable devices offer a promising alternative, providing a more convenient and scalable solution for long-term sleep monitoring. Compared to wrist-worn devices, smart rings offer a more stable signal acquisition environment, reducing motion artifacts and improving data reliability. This work investigates sleep staging using photoplethysmography (PPG)-derived instantaneous heart rate (IHR) signal and zero-crossing mode (ZCM) feature obtained from accelerometer data, both captured using a wearable smart ring. We propose a lightweight neural network model designed for wearable-based sleep staging, incorporating feature extraction, temporal modeling, and class balancing strategies. The IHR-based model consists of 503 k learnable parameters, while the ZCM-based model has 133 k learnable parameters, making them well-suited for efficient deployment on wearable devices. The proposed method is evaluated on a dataset of expert-annotated overnight sleep studies, using both IHR signal and ZCM features individually and in combination, in subject-independent cross-validation. The experimental results demonstrate that IHR features alone yield strong classification performance, achieving macro-average recall (unweighted average recall) values of 0.849, 0.805, 0.750, and 0.663 in two-class (wake vs. sleep), three-class (wake vs. non-rapid eye movement (NREM) sleep (N1, N2, N3) vs. REM sleep), four-class (wake vs. light sleep vs. deep sleep vs. REM sleep), and five-class (wake vs. N1 vs. N2 vs. N3 vs. REM) classification tasks, respectively. When combining IHR and ZCM features, classification performance improves further, reaching macro-average recall values of 0.866, 0.832, 0.772, and 0.671 in the respective tasks. These results highlight the effectiveness of IHR-based sleep staging and the additional benefit provided by movement-based ZCM features, particularly in two-, three-, and four-class sleep staging where we could achieve macro-average recall values of 0.750 or higher. The proposed smart ring-based system demonstrates strong potential for real-world sleep assessment by integrating multimodal physiological signals through lightweight neural networks, advancing non-invasive measurement and intelligent instrumentation.


  • Open Access

    Systematic Review and Meta-analysis of the Effects of Transcranial Electric Stimulation on Sleep in Healthy Adults

    by Hiroki Takeuchi, Yuki Motomura, Ayako Imamura, Mitsuaki Takemi, Koichi Hosomi, Akifumi Kishi

    Background: Transcranial electrical stimulation (tES) has gained attention because of its potential to modulate human sleep physiology. However, its efficacy in healthy populations remains unclear. Objectives: This systematic review and meta-analysis aimed to evaluate the effects of tES on sleep in healthy adults. Methods: A comprehensive literature search was conducted across five electronic databases from January 5 to 10, 2023, to retrieve articles administering tES and evaluating its effects on sleep in healthy adults. The Cochrane Collaboration’s tool was used to assess the risk of bias. The meta-analysis was performed using random-effects models and robust variance estimation, with subgroup analyses and meta-regression to examine conditional and moderation effects. Results: Among the 1,182 identified articles, 39 were included in the qualitative synthesis, and 14 ( N = 297) met the criteria for meta-analysis. The overall effect of tES on sleep was negligible (estimate: 0.00, 95% confidence interval [CI]: –0.18 to 0.19), with substantial heterogeneity. Subgroup meta-analysis revealed that pre-sleep tES prolonged sleep latency (estimate: –0.30, 95% CI: –0.49 to –0.11), whereas transcranial alternating current stimulation (tACS) increased total sleep time (estimate: 0.14, 95% CI: 0.01 to 0.27). Meta-regression analysis showed that tES efficacy was attenuated with increasing age ( β : –0.01, 95% CI: –0.02 to 0.00). Conclusions: Although tES does not appear to have a substantial overall effect on sleep, tACS may improve total sleep time, and pre-sleep offline tES may prolong sleep latency. Further well-designed studies are warranted to confirm these findings and minimize potential biases.


  • Open Access

    Novel Digital Markers of Sleep Dynamics: A Causal Inference Approach Revealing Age and Gender Phenotypes in Obstructive Sleep Apnea

    by Michal Bechny, Akifumi Kishi, Luigi Fiorillo, Julia van der Meer, Markus Schmidt, Claudio Bassetti, Athina Tzovara, Francesca Faraci

    Despite evidence that sleep-disorders alter sleep-stage dynamics, clinical practice resists including these parameters in PSG-reports. Leveraging the matrix of sleep-stage transition proportions, we propose (i) a general framework to quantify sleep-dynamics, (ii) several novel markers of their alterations, and (iii) demonstrate our approach using Obstructive Sleep Apnea (OSA), the most prevalent sleep-disorder. Using causal inference techniques, we address confounding in an observational clinical database and estimate markers personalized by age, gender, and OSA-severity. Importantly, our approach adjusts for five categories of sleep-wake-related comorbidities, a factor overlooked in existing research but present in 48.6% of OSA-subjects in our high-quality dataset. Key markers, such as NREM-REM-oscillations and sleep-stage-specific fragmentations, were increased across all OSA-severities and demographic groups. Additionally, we identified distinct gender-phenotypes, suggesting that females may be more vulnerable to awakenings and REM-sleep-disruptions. External validation of the transition markers on the SHHS database confirmed their robustness in detecting sleep-disordered-breathing (average AUROC = 66.4%). With advancements in automated sleep-scoring and wearable devices, our approach holds promise for developing low-cost screening tools for sleep-, neurodegenerative-, and psychiatric-disorders exhibiting altered sleep patterns.

  • Open Access

    Empowering Mental Health Monitoring Using a Macro-Micro Personalization Framework for Multimodal-Multitask Learning: Descriptive Study

    by Meishu Song, Zijiang Yang, Andreas Triantafyllopoulos, Zixing Zhang, Zhe Nan, Muxuan Tang, Hiroki Takeuchi, Toru Nakamura, Akifumi Kishi, Tetsuro Ishizawa, et al.

    Background: The field of mental health technology presently has significant gaps that need addressing, particularly in the domain of daily monitoring and personalized assessments. Current noninvasive devices such as wristbands and smartphones are capable of collecting a wide range of data, which has not yet been fully used for mental health monitoring. Objective: This study aims to introduce a novel dataset for personalized daily mental health monitoring and a new macro-micro framework. This framework is designed to use multimodal and multitask learning strategies for improved personalization and prediction of emotional states in individuals. Methods: Data were collected from 298 individuals using wristbands and smartphones, capturing physiological signals, speech data, and self-annotated emotional states. The proposed framework combines macro-level emotion transformer embeddings with micro-level personalization layers specific to each user. It also introduces a Dynamic Restrained Uncertainty Weighting method to effectively integrate various data types for a balanced representation of emotional states. Several fusion techniques, personalization strategies, and multitask learning approaches were explored. Results: The proposed framework was evaluated using the concordance correlation coefficient, resulting in a score of 0.503. This result demonstrates the framework’s efficacy in predicting emotional states. Conclusions: The study concludes that the proposed multimodal and multitask learning framework, which leverages transformer-based techniques and dynamic task weighting strategies, is superior for the personalized monitoring of mental health. The study indicates the potential of transforming daily mental health monitoring into a more personalized app, opening up new avenues for technology-based mental health interventions.


  • Macro-Sleep Staging With ECG-Derived Instantaneous Heart Rate and Respiration Signals and Multi-Input 1-D CNN–BiGRU

    by Roneel V. Sharan, Hiroki Takeuchi, Akifumi Kishi, Yoshiharu Yamamoto

    Millions of people worldwide are affected by sleep disorders. Polysomnography (PSG) is a type of sleep study that is used to diagnose sleep disorders, such as using sleep staging. However, PSG can be burdensome, time-consuming, expensive, and may not be readily accessible. Sleep cycles can cause fluctuations in heart rate and respiration which be estimated from electrocardiogram (ECG) signal. In addition, an ECG signal is easier to acquire compared to the multiparametric PSG. As such, in this work, we study the use of ECG data for sleep staging. In particular, the proposed method utilizes ECG-derived instantaneous heart rate (IHR) and ECG-derived respiration (EDR) signals. The IHR and EDR signals are input to a neural network that consists of a one-dimensional convolutional neural network to learn the temporal and spectral characteristics in short-time windows and a bidirectional gated recurrent unit to learn the long-term dependencies between the windows in both the forward and backward directions. The multi-input network analyzes the IHR and EDR signals independently. Features extracted from the analysis of the IHR and EDR signals are combined for classification of sleep stages. The proposed approach is evaluated on a dataset of 993 overnight sleep studies where the sleep stages are scored by experts. An average class accuracy of 83.8% is achieved in two-class staging (wake vs sleep), 79.3% in three-class staging (wake vs NREM sleep vs REM sleep), 73.7% in four-class staging (wake vs light sleep vs deep sleep vs REM sleep), and 63.5% in five-class staging (wake vs N1 vs N2 vs N3 vs REM). Our method is seen to be effective in macro-sleep staging, particularly in two, three, and four-class sleep staging, achieving class accuracy values greater than 76% for all classes, except light sleep. In addition, our method shows good generalizability in external validation.


  • Open Access

    Just-in-Time Adaptive Intervention for Stabilizing Sleep Hours of Japanese Workers: Microrandomized Trial

    by Hiroki Takeuchi, Tetsuro Ishizawa, Akifumi Kishi, Toru Nakamura, Kazuhiro Yoshiuchi, Yoshiharu Yamamoto

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Sleep disturbance is a major contributor to future health and occupational issues. Mobile health can provide interventions that address adverse health behaviors for individuals in a vulnerable health state in real-world settings (just-in-time adaptive intervention). Objective: This study aims to identify a subpopulation with vulnerable sleep state in daily life (study 1) and, immediately afterward, to test whether providing mobile health intervention improved habitual sleep behaviors and psychological wellness in real-world settings by conducting a microrandomized trial (study 2). Methods: Japanese workers (n=182) were instructed to collect data on their habitual sleep behaviors and momentary symptoms (including depressive mood, anxiety, and subjective sleep quality) using digital devices in a real-world setting. In study 1, we calculated intraindividual mean and variability of sleep hours, midpoint of sleep, and sleep efficiency to characterize their habitual sleep behaviors. In study 2, we designed and conducted a sleep just-in-time adaptive intervention, which delivered objective push-type sleep feedback messages to improve their sleep hours for a subset of participants in study 1 (n=81). The feedback messages were generated based on their sleep data measured on previous nights and were randomly sent to participants with a 50% chance for each day (microrandomization). Results: In study 1, we applied hierarchical clustering to dichotomize the population into 2 clusters (group A and group B) and found that group B was characterized by unstable habitual sleep behaviors (large intraindividual variabilities). In addition, linear mixed-effect models showed that the interindividual variability of sleep hours was significantly associated with depressive mood (β=3.83; P=.004), anxiety (β=5.70; P=.03), and subjective sleep quality (β=−3.37; P=.03). In study 2, we found that providing sleep feedback prolonged subsequent sleep hours (increasing up to 40 min; P=.01), and this effect lasted for up to 7 days. Overall, the stability of sleep hours in study 2 was significantly improved among participants in group B compared with the participants in study 1 (P=.001). Conclusions: This is the first study to demonstrate that providing sleep feedback can benefit the modification of habitual sleep behaviors in a microrandomized trial. The findings of this study encourage the use of digitalized health intervention that uses real-time health monitoring and personalized feedback.


  • Open Access

    Empowering Mental Health Monitoring Using a Macro-Micro Personalization Framework for Multimodal-Multitask Learning: Descriptive Study (Preprint)

    by Meishu Song, Zijiang Yang, Andreas Triantafyllopoulos, Zixing Zhang, Zhe Nan, Muxuan Tang, Hiroki Takeuchi, Toru Nakamura, Akifumi Kishi, Tetsuro Ishizawa, et al.

    BACKGROUND The field of mental health technology presently has significant gaps that need addressing, particularly in the domain of daily monitoring and personalized assessments. Current noninvasive devices such as wristbands and smartphones are capable of collecting a wide range of data, which has not yet been fully used for mental health monitoring. OBJECTIVE This study aims to introduce a novel dataset for personalized daily mental health monitoring and a new macro-micro framework. This framework is designed to use multimodal and multitask learning strategies for improved personalization and prediction of emotional states in individuals. METHODS Data were collected from 298 individuals using wristbands and smartphones, capturing physiological signals, speech data, and self-annotated emotional states. The proposed framework combines macro-level emotion transformer embeddings with micro-level personalization layers specific to each user. It also introduces a Dynamic Restrained Uncertainty Weighting method to effectively integrate various data types for a balanced representation of emotional states. Several fusion techniques, personalization strategies, and multitask learning approaches were explored. RESULTS The proposed framework was evaluated using the concordance correlation coefficient, resulting in a score of 0.503. This result demonstrates the framework’s efficacy in predicting emotional states. CONCLUSIONS The study concludes that the proposed multimodal and multitask learning framework, which leverages transformer-based techniques and dynamic task weighting strategies, is superior for the personalized monitoring of mental health. The study indicates the potential of transforming daily mental health monitoring into a more personalized app, opening up new avenues for technology-based mental health interventions. CLINICALTRIAL

  • Open Access

    Just-in-Time Adaptive Intervention for Stabilizing Sleep Hours of Japanese Workers: Microrandomized Trial (Preprint)

    by Hiroki Takeuchi, Tetsuro Ishizawa, Akifumi Kishi, Toru Nakamura, Kazuhiro Yoshiuchi, Yoshiharu Yamamoto

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Sleep disturbance is a major contributor to future health and occupational issues. Mobile health can provide interventions that address adverse health behaviors for individuals in a vulnerable health state in real-world settings (just-in-time adaptive intervention). Objective: This study aims to identify a subpopulation with vulnerable sleep state in daily life (study 1) and, immediately afterward, to test whether providing mobile health intervention improved habitual sleep behaviors and psychological wellness in real-world settings by conducting a microrandomized trial (study 2). Methods: Japanese workers (n=182) were instructed to collect data on their habitual sleep behaviors and momentary symptoms (including depressive mood, anxiety, and subjective sleep quality) using digital devices in a real-world setting. In study 1, we calculated intraindividual mean and variability of sleep hours, midpoint of sleep, and sleep efficiency to characterize their habitual sleep behaviors. In study 2, we designed and conducted a sleep just-in-time adaptive intervention, which delivered objective push-type sleep feedback messages to improve their sleep hours for a subset of participants in study 1 (n=81). The feedback messages were generated based on their sleep data measured on previous nights and were randomly sent to participants with a 50% chance for each day (microrandomization). Results: In study 1, we applied hierarchical clustering to dichotomize the population into 2 clusters (group A and group B) and found that group B was characterized by unstable habitual sleep behaviors (large intraindividual variabilities). In addition, linear mixed-effect models showed that the interindividual variability of sleep hours was significantly associated with depressive mood (β=3.83; P=.004), anxiety (β=5.70; P=.03), and subjective sleep quality (β=−3.37; P=.03). In study 2, we found that providing sleep feedback prolonged subsequent sleep hours (increasing up to 40 min; P=.01), and this effect lasted for up to 7 days. Overall, the stability of sleep hours in study 2 was significantly improved among participants in group B compared with the participants in study 1 (P=.001). Conclusions: This is the first study to demonstrate that providing sleep feedback can benefit the modification of habitual sleep behaviors in a microrandomized trial. The findings of this study encourage the use of digitalized health intervention that uses real-time health monitoring and personalized feedback.

  • Open Access

    Phenotypic Interindividual Differences in the Dynamic Structure of Sleep in Healthy Young Adults

    by Akifumi Kishi, Hans Pa Van Dongen

    Introduction: Evaluating the dynamic structure of sleep may yield new insights into the mechanisms underlying human sleep physiology. Methods: We analyzed data from a 12-day, 11-night, strictly controlled laboratory study with an adaptation night, 3 iterations of a baseline night followed by a recovery night after 36 h of total sleep deprivation, and a final recovery night. All sleep opportunities were 12 h in duration (22:00– 10:00) and recorded with polysomnography (PSG). The PSG records were scored for the sleep stages: rapid eye movement (REM) sleep; non-REM (NREM) stage 1 sleep (S1), stage 2 sleep (S2), and slow wave sleep (SWS); and wake (W). Phenotypic interindividual differences were assessed using indices of dynamic sleep structure – specifically sleep stage transitions and sleep cycle characteristics – and intraclass correlation coefficients across nights. Results: NREM/REM sleep cycles and sleep stage transitions exhibited substantial and stable interindividual differences that were robust across baseline and recovery nights, suggesting that mechanisms underlying the dynamic structure of sleep are phenotypic. In addition, the dynamics of sleep stage transitions were found to be associated with sleep cycle characteristics, with a significant relationship between the length of sleep cycles and the degree to which S2-to-W/S1 and S2-to-SWS transitions were in equilibrium. Discussion: Our findings are consistent with a model for the underlying mechanisms that involves three subsystems – characterized by S2-to-W/S1, S2-to-SWS, and S2-to-REM transitions – with S2 playing a hub-like role. Furthermore, the balance between the two subsystems within NREM sleep (S2-to-W/S1 and S2-to-SWS) may serve as a basis for the dynamic regulation of sleep structure and may represent a novel target for interventions aiming to improve sleep.


  • Open Access

    Just-in-time Adaptive Intervention for Stabilising Sleep Hours of Japanese Office Workers: A Micro-randomised Trial

    by Hiroki Takeuchi, Tetsuro Ishizawa, Akifumi Kishi, Toru Nakamura, Kazuhiro Yoshiuchi, Yoshiharu Yamamoto

    Sleep disturbance is a major contributor to future health and occupational issues. Mobile health (mHealth) can provide interventions that address adverse health behaviours for individuals in vulnerable health state, in real-world settings (just-in-time adaptive intervention, JITAI). Here, Japanese office workers were instructed to collect data on their habitual sleep behaviours (including sleep hours, midpoint of sleep, and sleep efficiency) and momentary symptoms (including depressive mood, anxiety, and subjective sleep quality) using digital devices in a real-world setting. In study 1, we utilised these data to identify a subpopulation that had problems in habitual sleep behaviours and found that unstable sleep hours were associated with disturbed momentary symptoms. Based on these findings, in study 2, we designed and conducted a sleep JITAI, which delivered objective push-type sleep feedback for stabilising their sleep hours, for some participants in study 1. Moreover, we employed micro-randomisation to examine the within-individual proximal effects of the intervention. Providing sleep feedback prolonged subsequent sleep hours, but this effect was attenuated over time. Changing sleep hours improved depressive mood and subjective sleep quality. Participants in study 2 had more stabilised sleep hours than those in study 1. This is the first mHealth study to demonstrate that sleep feedback proximally and distally improves sleep behaviours in a micro-randomised trial. The findings of this study encourage the use of digitalised health intervention trials that employs real-time health monitoring and personalised feedback.