Roben Delos Reyes

Roben Delos Reyes

Auto-generated profile, based on publicly available information

Roben Delos Reyes

Affiliation School of Computing and Information Systems, The University of Melbourne, Parkville, Victoria, Australia

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
22 February 2023 in Journal of Medical Internet Research
Verified
Journal Article
Open access
VLVu Linh Le
Vu Linh Le
DKDaewoo Kim
Daewoo Kim
ECEunsung Cho
Eunsung Cho
HJHyeryung Jang
Hyeryung Jang
RRRoben Delos Reyes
Roben Delos Reyes
JKJeong-Whun Kim
Jeong-Whun Kim
Background: Multinight monitoring can be helpful for the diagnosis and management of obstructive sleep apnea (OSA). For this purpose, it is necessary to be able to detect OSA in real time in a noisy home environment. Sound-based OSA assessment holds great potential since it can be integrated with smartphones to provide full noncontact monitoring of OSA at home. Objective: The purpose of this study is to develop a predictive model that can detect OSA in real time, even in a home environment where various noises exist. Methods: This study included 1018 polysomnography (PSG) audio data sets, 297 smartphone audio data sets synced with PSG, and a home noise data set containing 22,500 noises to train the model to predict breathing events, such as apneas and hypopneas, based on breathing sounds that occur during sleep. The whole breathing sound of each night was divided into 30-second epochs and labeled as “apnea,” “hypopnea,” or “no-event,” and the home noises were used to make the model robust to a noisy home environment. The performance of the prediction model was assessed using epoch-by-epoch prediction accuracy and OSA severity classification based on the apnea-hypopnea index (AHI). Results: Epoch-by-epoch OSA event detection showed an accuracy of 86% and a macro F1-score of 0.75 for the 3-class OSA event detection task. The model had an accuracy of 92% for “no-event,” 84% for “apnea,” and 51% for “hypopnea.” Most misclassifications were made for “hypopnea,” with 15% and 34% of “hypopnea” being wrongly predicted as “apnea” and “no-event,” respectively. The sensitivity and specificity of the OSA severity classification (AHI≥15) were 0.85 and 0.84, respectively. Conclusions: Our study presents a real-time epoch-by-epoch OSA detector that works in a variety of noisy home environments. Based on this, additional research is needed to verify the usefulness of various multinight monitoring and real-time diagnostic technologies in the home environment.

24 March 2023 in eLife
Verified
Journal Article
Open access
MAMark Borris D Aldonza
Mark Borris D Aldonza
JCJunghwa Cha
Junghwa Cha
IYInsung Yong
Insung Yong
JKJayoung Ku
Jayoung Ku
PSPavel Sinitcyn
Pavel Sinitcyn
YKYoosik Kim
Yoosik Kim
Cancer secretome is a reservoir for aberrant glycosylation. How therapies alter this post- translational cancer hallmark and the consequences thereof remain elusive. Here, we show that an elevated secretome fucosylation is a pan-cancer signature of both response and resistance to multiple targeted therapies. Large-scale pharmacogenomics revealed that fucosylation genes display widespread association with resistance to these therapies. In cancer cell cultures, xenograft mouse models, and patients, targeted kinase inhibitors distinctively induced core fucosylation of secreted proteins less than 60 kDa. Label-free proteomics of N-glycoproteomes identified fucosylation of the antioxidant PON1 as a critical component of the therapy-induced secretome (TIS). N-glycosylation of TIS and target core fucosylation of PON1 are mediated by the fucose salvage-FUT8-SLC35C1 axis with PON3 directly modulating GDP-Fuc transfer on PON1 scaffolds. Core fucosylation in the Golgi impacts PON1 stability and folding prior to secretion, promoting a more degradation-resistant PON1. Global and PON1-specific secretome de-N-glycosylation both limited the expansion of resistant clones in a tumor regression model. We defined the resistance-associated transcription factors (TFs) and genes modulated by the N-glycosylated TIS via a focused and transcriptome-wide analyses. These genes characterize the oxidative stress, inflammatory niche, and unfolded protein response as important factors for this modulation. Our findings demonstrate that core fucosylation is a common modification indirectly induced by targeted therapies that paradoxically promotes resistance.

1 December 2021 in Nature and Science of Sleep
Verified
Journal Article
Open access
PDF file
JHJung Kyung Hong
Jung Kyung Hong
TLTaeyoung Lee
Taeyoung Lee
RRRoben Deocampo Delos Reyes
Roben Deocampo Delos Reyes
JHJoonki Hong
Joonki Hong
HTHai Hong Tran
Hai Hong Tran
IYIn-Young Yoon
In-Young Yoon
Study Objectives: Automated sleep stage scoring is not yet vigorously used in practice because of the black-box nature and the risk of wrong predictions. The objective of this study was to introduce a confidence-based framework to detect the possibly wrong predictions that would inform clinicians about which epochs would require a manual review and investigate the potential to improve accuracy for automated sleep stage scoring. Methods: We used 702 polysomnography studies from a local clinical dataset (SNUBH dataset) and 2804 from an open dataset (SHHS dataset) for experiments. We adapted the state-of-the-art TinySleepNet architecture to train the classifier and modified the ConfidNet architecture to train an auxiliary confidence model. For the confidence model, we developed a novel method, Dropout Correct Rate (DCR), and the performance of it was compared with other existing methods. Results: Confidence estimates (0.754) reflected accuracy (0.758) well in general. The best performance for differentiating correct and wrong predictions was shown when using the DCR method (AUROC: 0.812) compared to the existing approaches which largely failed to detect wrong predictions. By reviewing only 20% of epochs that received the lowest confidence values, the overall accuracy of sleep stage scoring was improved from 76% to 87%. For patients with reduced accuracy (ie, individuals with obesity or severe sleep apnea), the possible improvement range after applying confidence estimation was even greater. Conclusion: To the best of our knowledge, this is the first study applying confidence estimation on automated sleep stage scoring. Reliable confidence estimates by the DCR method help screen out most of the wrong predictions, which would increase the reliability and interpretability of automated sleep stage scoring.

5 January 2026 in PLOS Digital Health
Verified
Journal Article
Open access
PDF file
SOSebastián Andrés Cajas Ordóñez
Sebastián Andrés Cajas Ordóñez
RCRowell Castro
Rowell Castro
LCLeo Anthony Celi
Leo Anthony Celi
RRRoben Delos Reyes
Roben Delos Reyes
JEJustin Engelmann
Justin Engelmann
JSJana Sedlakova
Jana Sedlakova
Contemporary medical AI systems exhibit a critical vulnerability: they deliver confident predictions without mechanisms to express uncertainty or acknowledge limitations, leading to dangerous overreliance in clinical settings. This paper introduces the BODHI (Bridging, Open, Discerning, Humble, Inquiring) framework, a dual-reflective architecture grounded in two essential epistemic virtues: curiosity and humility, as foundational design principles for healthcare AI. Curiosity drives systems to actively explore diagnostic uncertainty, seek additional information when faced with ambiguous presentations, and recognize when training distributions fail to match clinical reality. Humility provides complementary restraint, enabling uncertainty quantification, boundary recognition, and appropriate deference to human expertise. We demonstrate how these virtues function synergistically in a dynamic feedback loop, preventing both reckless exploration and excessive caution while supporting collaborative clinical decision-making. Drawing from psychological theories of curiosity and cross-species evidence of epistemic humility, we argue that these capacities represent fundamental biological design principles essential for systems operating in high-stakes, uncertain environments. The BODHI framework addresses systemic failures in medical AI deployment, from biased training data to institutional workflow pressures, by embedding uncertainty awareness and collaborative restraint into foundational system architecture. Key implementation features include calibrated confidence measures, out-of-distribution detection, curiosity-driven escalation protocols, and transparency mechanisms that adapt to clinical context. Rather than pursuing algorithmic perfection through pure optimization, we advocate for human-AI partnerships that enhance clinical reasoning through mutual accountability and calibrated trust. This approach represents a paradigm shift from overconfident automation toward collaborative systems that embody the wisdom to pause, reflect, and defer when appropriate.

17 September 2024 in Computers in Biology and Medicine
Verified
Journal Article
Open access
RRRoben Delos Reyes
Roben Delos Reyes
DCDaniel Capurro
Daniel Capurro
NGNic Geard
Nic Geard
Computer simulations of emergency departments (EDs) are tools that can support managing and optimising ED operations. A core component of ED simulation models is patient trajectories, defined as the series of activities patients undergo in the ED from arrival to discharge. The combined duration of these activities, and waiting times between them, determines a patient's length of stay (LOS). Patient trajectories are often calibrated and validated solely based on the estimated acuity of patients assigned upon arrival. However, acuity is a prospective patient indicator that inconsistently reflects patients' actual urgency and resource usage as seen retrospectively upon discharge. Here, we propose a data-driven ED simulation model in which patient trajectories are modelled based on both acuity and retrospective patient indicators. We show that including retrospective patient indicators recovers the observed LOS distributions more accurately than when using acuity alone. We also demonstrate how the use of retrospective patient indicators leads to more plausible estimates of the impact of increased stress in the ED on patients' LOS. Our work exemplifies how we can better utilise ED data to make the development and evaluation of ED simulation models more accurate and robust, enabling them to provide more reliable and useful operational insights.

6 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
KSKyunghwan Son
Kyunghwan Son
SASungsoo Ahn
Sungsoo Ahn
RRRoben Delos Reyes
Roben Delos Reyes
JSJinwoo Shin
Jinwoo Shin
YYYung Yi
Yung Yi
QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable of learning the largest class of joint-action value functions up to date. However, despite its strong theoretical guarantee, it has shown poor empirical performance in complex environments, such as Starcraft Multi-Agent Challenge (SMAC). In this paper, we identify the performance bottleneck of QTRAN and propose a substantially improved version, coined QTRAN++. Our gains come from (i) stabilizing the training objective of QTRAN, (ii) removing the strict role separation between the action-value estimators of QTRAN, and (iii) introducing a multi-head mixing network for value transformation. Through extensive evaluation, we confirm that our diagnosis is correct, and QTRAN++ successfully bridges the gap between empirical performance and theoretical guarantee. In particular, QTRAN++ newly achieves state-of-the-art performance in the SMAC environment. The code will be released.