Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks51 from public data
- Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms408
This diagnostic accuracy study evaluates whether artificial intelligence can overcome human mammography interpretation limits with a rigorous, unbiased evaluation of machine learning algorithms.
- 242
- Self-Path: Self-Supervision for Classification of Pathology Images With Limited Annotations201
The results show that Self-Path with the pathology-specific pretext tasks achieves state-of-the-art performance for semi-supervised learning when small amounts of labeled data are available and improves domain adaptation for histopathology image classification when there is no labeled data available for the target domain.
- Sparsity enables estimation of both subcortical and cortical activity from MEG and EEG154
It is shown here that it is difficult to resolve subcortical sources because distributed cortical activity can explain the MEG and EEG patterns generated by deep sources, and it is demonstrated that if the cortical activity is spatially sparse, both cortical and subcorting sources can be resolved with M/EEG.
- Speed adaptation in a powered transtibial prosthesis controlled with a neuromuscular model110
A data-driven muscle–tendon model is used that produces estimates of the activation, force, length and velocity of the major muscles spanning the ankle to derive local feedback loops that may be critical in the control of those muscles during walking.
- The Singapore National Precision Medicine Strategy95
Singapore’s efforts to implement a National Precision Medicine Strategy through the integration of genomic, clinical and lifestyle data of up to one million Singaporean individuals are discussed.
- Human Leg Model Predicts Ankle Muscle-Tendon Morphology, State, Roles and Energetics in Walking64
The framework outlined here suggests that the dynamical interplay between leg structure and neural control may be key to the high walking economy of humans, and has implications as a means to obtain insight into empirically inaccessible features of individual muscle and tendons in biomechanical tasks.
- Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications42
This work introduces a practical and theoretically grounded transition sampling approach to address action imbalance during offline RL training and shows that the proposed approach enables substantial improvements in expected health outcomes and in consistency with relevant practice and safety guidelines.
- Towards Practical Unsupervised Anomaly Detection on Retinal Images38
This work establishes a strong unsupervised baseline for image-based anomaly detection, alongside a flexible and scalable approach for screening applications, and shows the ability to leverage very small numbers of labelled anomalies to improve performance.
- 30
- Reference-free removal of EEG-fMRI ballistocardiogram artifacts with harmonic regression30
This work model the BCG artifact using a harmonic basis, pose the artifact removal problem as a local harmonic regression analysis, and develop an efficient maximum likelihood algorithm to estimate and remove BCG artifacts that outperforms commonly used reference-based and component analysis techniques.
- High-Resolution Digital Phenotypes From Consumer Wearables and Their Applications in Machine Learning of Cardiometabolic Risk Markers: Cohort Study25
High-resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance the prediction of cardiometabolic disease risk and could enable more proactive and personalized health management.
- Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring24
This work proposes a framework inspired by nurse-initiated clinical symptom monitoring conversations to construct a simulated human-human dialogue dataset, embodying linguistic characteristics of spoken interactions like thinking aloud, self-contradiction, and topic drift, and demonstrates the feasibility for efficient and effective extraction, retrieval and comprehension of symptom checking information discussed in multi-turn human- human spoken conversations.
- Consistency-Based Semi-supervised Evidential Active Learning for Diagnostic Radiograph Classification19
A novel Consistency-based Semi-supervised Evidential Active Learning framework is introduced that combines consistency-based semi-supervised learning with uncertainty-based active learning and can substantially improve accuracy on rarer abnormalities with fewer labelled samples.
- Assessing Risk in Implementing New Artificial Intelligence Triage Tools—How Much Risk is Reasonable in an Already Risky World?18
The outcomes of a risk–benefit analysis are discussed to argue that the proposed implementation strategy is ethically appropriate and aligns with improvement-focused and systemic approaches to implementation, especially the learning health systems framework (LHS) to ensure safety, efficacy, and ongoing learning.
- Artificial Intelligence and Radiology in Singapore: Championing a New Age of Augmented Imaging for Unsurpassed Patient Care18
A "Centaur" model is proposed and described as a promising avenue for enabling the interfacing between AI and radiologists and the barriers to the widespread adoption of AI in radiology are reviewed.
- Semi-supervised Classification of Diagnostic Radiographs with NoTeacher: A Teacher that is Not Mean16
A novel SSL method named NoTeacher is introduced that incorporates a probabilistic graphical model to maximize mutual agreement between student networks, thereby eliminating the need for a teacher network and achieves over 90% of the fully supervised AUROC with less than 5% labeling budget.
- Semi-supervised classification of radiology images with NoTeacher: A teacher that is not mean15
NoTeacher is introduced, a novel consistency-based SSL framework which incorporates probabilistic graphical models and outperforms established SSL methods with minimal hyperparameter tuning, and has implications as a principled and practical option for semi-supervised learning in radiology applications.
- 14
- 11
- 11
- Context Aggregation with Topic-focused Summarization for Personalized Medical Dialogue Generation10
This work investigates the potential of harnessing large language models for personalized medical dialogue generation, and adopts topic-focused summarization to distill core information from the dialogue history and use such information to guide the conversation flow and generated content.
- 8
- CareNets: Efficient Homomorphic CNN for High Resolution Images8
The results show that CareNets achieves over 32.78 × speedup, 45 × improvement in memory efficiency, and 5851 × reduction in transferred message size while maintaining accuracy within 3% of the non-encrypted CNN baselines.
- 7
- A drug mix and dose decision algorithm for individualized type 2 diabetes management6
An AI Drug mix and dose Advisor for glycemic management that provides drug-dose recommendations to improve outcomes for individual T2D patients, it could be used for clinical decision support at point-of-care, especially in resource-limited settings.
- 6
- 6
- 5
- Attention-based Semantic Priming for Slot-filling5
It is proposed that an attention-based RNN architecture can be used to simulate semantic priming for sequence labelling, and pre-trained word embeddings are employed to characterize the semantic relationship between utterances and labels.
- 4
- 4
- Uncertainty Characterization for Predictive Analytics with Clinical Time Series Data3
This research was supported by grant funding from A*STAR, Singapore (SSF A1818g0044 and IAF H19/01/a0-023).
- Joint Learning of Word and Label Embeddings for Sequence Labelling in Spoken Language Understanding3
The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association from the training data and can achieve state-of-the-art performance with much fewer trainable parameters.
- A computational framework to study neural-structural interactions in human walking3
This dissertation aims to demonstrate the power of data-driven, evidence-based learning to improve the quality of human experience in the natural world.
- 2
- Characterization of Telecare Conversations on Lifestyle Management and Their Relation to Health Care Utilization for Patients with Heart Failure: Mixed Methods Study2
Findings indicate that lifestyle-focused calls entail short, intense discussions with greater emphasis on understanding patient experience and coaching than on clinical content, which could inform ways to enhance telehealth programs for self-care management in chronic conditions.
- 2
- 2
- Analyzing Code Embeddings for Coding Clinical Narratives2
Comparing different ways to represent, or embed, the codes based on their textual, structural and statistical characteristics, using a single deep learning base-line model in quantitative evaluations on discharge reports from the MIMIC-III Intensive Care Unit database shows that code embeddings are important for predicting ambiguous and oblique codes.
- Algorithms for enhanced spatiotemporal imaging of human brain function2
The algorithms developed in this thesis provide novel opportunities to non-invasively relate fast timescale measures of neuronal activity with their underlying regional brain dynamics, thus paving a way for enhanced spatiotemporal imaging of human brain function.
- Secure bioinformatics: privacy-preserving federated analytics using homomorphic encryption1
The proposed solution achieves over 99.9% accuracy relative to plaintext analyses, while maintaining scalable runtime performance with increasing data size and number of participating sites, demonstrate the feasibility of secure federated analytics for practical bioinformatics applications involving sensitive data.
- Uncertainty Modeling for Machine Comprehension Systems using Efficient Bayesian Neural Networks1
This work proposes a hybrid neural architecture to quantify model uncertainty using Bayesian weight approximation but boosts up the inference speed by 80% relative at test time, and applies it for a clinical dialogue comprehension task.
- –
- Consistency-based Semi-supervised Evidential Active Learning Framework for Robust Classification of Radiology Images–
CSEAL is a principled SSAL framework leveraging evidential learning for reliable estimation of predictive uncertainty for consistency enforcement and prioritised sampling, and offers new opportunities to enhance the efficiency of clinical image annotation and model development workflows.
- MediPhen: Prompt-Based LLM Reasoning with Synthesized Multimodal Clinical Knowledge for Zero-Shot Multi-morbidity Phenotyping–
MediPhen introduces a framework for adapting LLMs to zero-shot disease phenotyping by incorporating extracted clinical entities, their relations, and lab narratives from EHRs, integrating a clinical knowledgebase to guide phenotype classification and enhance LLM transfer learning performance, and an explanation module that leverages chain-of-thought prompting to improve clinical reasoning.
- –
- Graph-Based Modeling of Behavioral Transitions for Digital Health Applications: Trajectory Analysis Framework–
A graph-based behavioral trajectory model that models behavioral transitions as shortest paths through user similarity graphs provides an interpretable framework for modeling behavioral transitions in digital health applications and captures key dynamics that support personalized intervention design.
- –
- A Predictive Analytics Methodology to Assess and Optimize Readmission Risk in Heart Failure Patients–
A predictive modeling and decision support framework that integrates machine learning and optimization for personalized clinical decision support is described and the ability to predict and optimize re-admission risk in a clinically meaningful manner is demonstrated.
- Sparse Representation Learning Approach Resolves Deep Sources Underlying MEG and EEG Data.–
It is demonstrated that deep sources underlying M/EEG and MEG and electroencephalography can be resolved with a sparse representation learning approach and a novel source estimation algorithm is introduced to characterize neural currents within subcortical structures.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.