Hyatt Moore

Dr. Hyatt Moore

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
9 December 2014 in PLOS ONE
Verified
Journal Article
Open access
PDF file
HMHyatt Moore
Hyatt Moore
Eileen B LearyEileen B Leary
Eileen B Leary
SLSeo-Young Lee
Seo-Young Lee
OCOscar Carrillo
Oscar Carrillo
RSRobin Stubbs
Robin Stubbs
EMEmmanuel Mignot
Emmanuel Mignot
Periodic Limb Movements (PLMs) are episodic, involuntary movements caused by fairly specific muscle contractions that occur during sleep and can be scored during nocturnal polysomnography (NPSG). Because leg movements (LM) may be accompanied by an arousal or sleep fragmentation, a high PLM index (i.e. average number of PLMs per hour) may have an effect on an individual’s overall health and wellbeing. This study presents the design and validation of the Stanford PLM automatic detector (S-PLMAD), a robust, automated leg movement detector to score PLM. NPSG studies from adult participants of the Wisconsin Sleep Cohort (WSC, n = 1,073, 2000–2004) and successive Stanford Sleep Cohort (SSC) patients (n = 760, 1999–2007) undergoing baseline NPSG were used in the design and validation of this study. The scoring algorithm of the S-PLMAD was initially based on the 2007 American Association of Sleep Medicine clinical scoring rules. It was first tested against other published algorithms using manually scored LM in the WSC. Rules were then modified to accommodate baseline noise and electrocardiography interference and to better exclude LM adjacent to respiratory events. The S-PLMAD incorporates adaptive noise cancelling of cardiac interference and noise-floor adjustable detection thresholds, removes LM secondary to sleep disordered breathing within 5 sec of respiratory events, and is robust to transient artifacts. Furthermore, it provides PLM indices for sleep (PLMS) and wake plus periodicity index and other metrics. To validate the final S-PLMAD, experts visually scored 78 studies in normal sleepers and patients with restless legs syndrome, sleep disordered breathing, rapid eye movement sleep behavior disorder, narcolepsy-cataplexy, insomnia, and delayed sleep phase syndrome. PLM indices were highly correlated between expert, visually scored PLMS and automatic scorings (r2 = 0.94 in WSC and r2 = 0.94 in SSC). In conclusion, The S-PLMAD is a robust and high throughput PLM detector that functions well in controls and sleep disorder patients.

6 February 2025 in medRxiv
Verified
Preprint
Open access
PDF file
RTRahul Thapa
Rahul Thapa
MKMagnus Ruud Kjaer
Magnus Ruud Kjaer
BHBryan He
Bryan He
ICIan Covert
Ian Covert
HMHyatt Moore
Hyatt Moore
JZJames Y Zou
James Y Zou
Sleep is a fundamental biological process with profound implications for physical and mental health, yet our understanding of its complex patterns and their relationships to a broad spectrum of diseases remains limited. While polysomnography (PSG), the gold standard for sleep analysis, captures rich multimodal physiological data, analyzing these measurements has been challenging due to limited flexibility across recording environments, poor generalizability across cohorts, and difficulty in leveraging information from multiple signals simultaneously. To address this gap, we curated over 585,000 hours of high-quality sleep recordings from approximately 65,000 participants across multiple cohorts and developed SleepFM, a multimodal sleep foundation model trained with a novel contrastive learning approach, designed to accommodate any PSG montage. SleepFM produces informative sleep embeddings that enable predictions of future diseases. We systematically demonstrate that SleepFM embeddings can predict 130 future diseases, as modeled by Phecodes, with C-Index and AUROC of at least 0.75 on held-out participants (Bonferroni-corrected p < 0.01). This includes accurate predictions for death (C-Index: 0.84 [95% CI: 0.81–0.87]), heart failure (C-Index: 0.80 [95% CI: 0.77–0.83]), chronic kidney disease (C-Index: 0.79 [95% CI: 0.77–0.81]), dementia (C-Index: 0.85 [95% CI: 0.82–0.87]), stroke (C-Index: 0.78 [95% CI: 0.76–0.81]), atrial fibrillation (C-Index: 0.78 [95% CI: 0.75–0.81]), and myocardial infarction (C-Index: 0.81 [95% CI: 0.78–0.84]). The model’s generalizability was further validated through strong performance on the Sleep Heart Health Study (SHHS), a dataset unseen during pre-training. Additionally, SleepFM demonstrates strong performance on traditional sleep analysis tasks, achieving competitive results in both sleep staging (mean F1 scores: 0.70–0.78) and sleep apnea diagnosis (AUROC: 0.90–0.94). Beyond these standard applications, our analysis reveals that specific sleep stages and physiological signals carry distinct predictive power for different diseases. This work demonstrates how foundation models can leverage sleep polysomnography data to uncover the extensive relationship between sleep physiology and future disease risk.

9 August 2023 in Sleep Health
Verified
Journal Article
Closed access
KCKatie L.J. Cederberg
Katie L.J. Cederberg
VSVicente Peris Sempere
Vicente Peris Sempere
LLLing Lin
Ling Lin
JZJing Zhang
Jing Zhang
ELEileen B. Leary
Eileen B. Leary
EMEmmanuel Mignot
Emmanuel Mignot

1 April 2014 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
HMHyatt Moore
Hyatt Moore
OAOlivier Andlauer
Olivier Andlauer
NSNoah Simon
Noah Simon
EMEmmanuel Mignot
Emmanuel Mignot

1 June 2023 in Journal for the Measurement of Physical Behaviour
Verified
Journal Article
Open access
PDF file
JYJingzhi Yu
Jingzhi Yu
KKKristopher Kapphahn
Kristopher Kapphahn
HMHyatt Moore
Hyatt Moore
FHFarish Haydel
Farish Haydel
TRThomas N. Robinson
Thomas N. Robinson
MDManisha Desai
Manisha Desai
Background: Clustering, a class of unsupervised machine learning methods, has been applied to physical activity data recorded by accelerometers to discover unique patterns of physical activity and health outcomes. The prediction strength metric provides a criterion to determine the optimal number of clusters for clustering methods. The aim of this study is to provide specific guidance for applying prediction strength to time series accelerometer data. Methods: For this purpose, we designed an extensive simulation study. We created a synthetic data set of accelerometer data using data from a childhood obesity management trial. We evaluated the role of a prespecified threshold of the prediction strength metric as a key input parameter. We compared the recommended threshold (between 0.8 and 0.9) with an approach we developed (Local Maxima). Results: The choice of threshold had a large impact on performance. When the noise level increased (greater overlap between true clusters), lower thresholds outperformed the recommended threshold, which tended to underestimate the true number of clusters. In addition, we found that sorting the data by magnitude of intensity in windows within the time series of interest prior to clustering alleviated sensitivity to threshold choice. Furthermore, for accelerometer data, we recommend that the Local Maxima approach be utilized together with a graphical evaluation of the prediction strength metric function over values of k. Finally, we strongly suggest sorting of the data prior to clustering if sorting retains meaning for the research question at hand. Conclusion: Our recommendations can help future researchers discover more robust patterns from accelerometer data.

1 June 2023 in Journal for the Measurement of Physical Behaviour
Verified
Journal Article
Open access
PDF file
SRSahej Randhawa
Sahej Randhawa
MSManoj Kumar Sharma
Manoj Kumar Sharma
MFMadalina Fiterau
Madalina Fiterau
JBJorge A. Banda
Jorge A. Banda
FHFarish Haydel
Farish Haydel
MDManisha Desai
Manisha Desai
Background: Accelerometers are used to objectively measure movement in free-living individuals. Distinguishing nonwear from sleep and sedentary behavior is important to derive accurate measures of physical activity, sedentary behavior, and sleep. We applied statistical learning approaches to examine their promise in detecting nonwear time and compared the results with commonly used wear time (WT) algorithms. Methods: Fifteen children, aged 4–17, wore an ActiGraph wGT3X-BT monitor on their hip during overnight polysomnography. We applied Hidden Markov Models (HMM) and Gaussian Mixture Models (GMM) to classify states of nonwear and wear in triaxial acceleration data. Performance of methods was compared with WT algorithms across two conditions with differing amounts of consecutive nonwear. Clinical scoring of polysomnography served as the gold standard. Results: When the length of nonwear was less than or equal to WT algorithms’ predefined thresholds for consecutive nonwear time, GMM methods yielded improved classification error, specificity, positive predictive value, and negative predictive value over commonly used algorithms. HMM was superior to one algorithm for sensitivity and negative predictive value. When the length of nonwear was longer, results were mixed, with the commonly used algorithms performing better on some parameters but GMM with the greatest specificity. However, all approached the upper limits of performance for almost all metrics. Conclusions: GMM and HMM demonstrated robust, consistently strong performance across multiple conditions, surpassing or remaining competitive with commonly used WT algorithms which had marked inaccuracy when nonwear time periods were shorter. Of the two statistical learning algorithms, GMM was superior to HMM.