Dilruk Perera

Daniel J. Tan, Qianyi Xu, Kay Choong See et al.

In healthcare, multi-organ system diseases pose unique and significant challenges as they impact multiple physiological systems concurrently, demanding complex and coordinated treatment strategies. Despite recent advancements in the AI based clinical decision support systems, these solutions only focus on individual organ systems, failing to account for complex interdependencies between them. This narrow focus greatly hinders their effectiveness in recommending holistic and clinically actionable treatments in the real world setting. To address this critical gap, we propose a novel Hierarchical Multi-Agent Reinforcement Learning (HMARL) framework. Our architecture deploys specialized and dedicated agents for each organ system and facilitates inter-agent communication to enable synergistic decision-making across organ systems. Furthermore, we introduce a dual-layer state representation technique that contextualizes patient conditions at both global and organ-specific levels, improving the accuracy and relevance of treatment decisions. We evaluate our HMARL solution on the task of sepsis management, a common and critical multi-organ disease, using both qualitative and quantitative metrics. Our method learns effective, clinically aligned treatment policies that considerably improve patient survival. We believe this framework represents a significant advancement in clinical decision support systems, introducing the first RL solution explicitly designed for multi-organ treatment recommendations. Our solution moves beyond prevailing simplified, single-organ models that fall short in addressing the complexity of multi-organ diseases.

Qianyi Xu, Gousia Habib, Feng Wu et al.

Reinforcement Learning (RL) offers a powerful framework for optimizing dynamic treatment regimes (DTRs). However, clinical RL is fundamentally bottlenecked by reward engineering: the challenge of defining signals that safely and effectively guide policy learning in complex, sparse offline environments. Existing approaches often rely on manual heuristics that fail to generalize across diverse pathologies. To address this, we propose an automated pipeline leveraging Large Language Models (LLMs) for offline reward design and verification. We formulate the reward function using potential functions consisted of three core components: survival, confidence, and competence. We further introduce quantitative metrics to rigorously evaluate and select the optimal reward structure prior to deployment. By integrating LLM-driven domain knowledge, our framework automates the design of reward functions for specific diseases while significantly enhancing the performance of the resulting policies.

Rayner Kay Jin Tan, Dilruk Perera, Salomi Arasaratnam et al.

Artificial Intelligence applications have shown promise in the management of pandemics and have been widely used to assist the identification, classification, and diagnosis of medical images. In response to the global outbreak of Monkeypox (Mpox), the HeHealth.ai team leveraged an existing tool to screen for sexually transmitted diseases to develop a digital screening test for symptomatic Mpox through AI approaches. Prior to the global outbreak of Mpox, the team developed a smartphone app, where app users can use their own smartphone cameras to take pictures of their own penises to screen for symptomatic STD. The AI model was initially developed using 5000 cases and use a modified convolutional neural network to output prediction scores across visually diagnosable penis pathologies including Syphilis, Herpes Simplex Virus, and Human Papilloma Virus. From June 2022 to October 2022, a total of about 22,000 users downloaded the HeHealth app, and about 21,000 images have been analyzed using HeHealth AI technology. We then engaged in formative research, stakeholder engagement, rapid consolidation images, a validation study, and implementation of the tool from July 2022. From July 2022 to October 2022, a total of 1000 Mpox related images had been used to train the Mpox symptom checker tool. Our digital symptom checker tool showed accuracy of 87% to rule in Mpox and 90% to rule out symptomatic Mpox. Several hurdles identified included issues of data privacy and security for app users, initial lack of data to train the AI tool, and the potential generalizability of input data. We offer several suggestions to help others get started on similar projects in emergency situations, including engaging a wide range of stakeholders, having a multidisciplinary team, prioritizing pragmatism, as well as the concept that big data in fact is made up of small data.

Daniel Jason Tan, Jiayang Chen, Dilruk Perera et al.

ICU enteral feeding remains sub-optimal due to limited personalization and uncertainty about appropriate calorie, protein, and fluid targets, particularly under rapidly changing metabolic demands and heterogeneous patient responses. This study introduces DeepEN, a reinforcement learning (RL)-based framework that personalizes enteral nutrition (EN) dosing for critically ill patients using electronic health record data. DeepEN was trained on over 11,000 ICU patients from the MIMIC-IV database to generate 4-hourly, patient-specific targets for caloric, protein, and fluid intake. The model's state space integrates demographics, comorbidities, vital signs, laboratory results, and prior interventions relevant to nutritional management, while its reward function balances short-term physiological and nutrition-related goals with long-term survival. A dueling double deep Q-network with Conservative Q-Learning regularization is used to ensure safe and reliable policy learning from retrospective data. DeepEN achieved a 3.7 $\pm$ 0.17 percentage-point absolute reduction in estimated mortality compared with the clinician policy (18.8% vs 22.5%) and higher expected returns compared with guideline-based dosing (11.89 vs 8.11), with improvements in key nutritional biomarkers. U-shaped associations between deviations from clinician dosing and mortality suggest that the learned policy aligns with high-value clinician actions while diverging from suboptimal ones. These findings demonstrate the feasibility of conservative offline RL for individualized EN therapy and suggest that data-driven personalization may improve outcomes beyond guideline- or heuristic-based approaches.

Dilruk Perera, Gousia Habib, Qianyi Xu et al.

Reinforcement learning (RL) marks a fundamental shift in how artificial intelligence is applied in healthcare. Instead of merely predicting outcomes, RL actively decides interventions with long term goals. Unlike traditional models that operate on fixed associations, RL systems learn through trial, feedback, and long-term reward optimization, introducing transformative possibilities and new risks. From an information fusion lens, healthcare RL typically integrates multi-source signals such as vitals, labs clinical notes, imaging and device telemetry using temporal and decision-level mechanisms. These systems can operate within centralized, federated, or edge architectures to meet real-time clinical constraints, and naturally span data, features and decision fusion levels. This survey explore RL's rise in healthcare as more than a set of tools, rather a shift toward agentive intelligence in clinical environments. We first structure the landscape of RL techniques including model-based and model-free methods, offline and batch-constrained approaches, and emerging strategies for reward specification and uncertainty calibration through the lens of healthcare constraints. We then comprehensively analyze RL applications spanning critical care, chronic disease, mental health, diagnostics, and robotic assistance, identifying their trends, gaps, and translational bottlenecks. In contrast to prior reviews, we critically analyze RL's ethical, deployment, and reward design challenges, and synthesize lessons for safe, human-aligned policy learning. This paper serves as both a a technical roadmap and a critical reflection of RL's emerging transformative role in healthcare AI not as prediction machinery, but as agentive clinical intelligence.

Dilruk Perera, Roger Zimmermann

The abundance of information in web applications make recommendation essential for users as well as applications. Despite the effectiveness of existing recommender systems, we find two major limitations that reduce their overall performance: (1) inability to provide timely recommendations for both new and existing users by considering the dynamic nature of user preferences, and (2) not fully optimized for the ranking task when using implicit feedback. Therefore, we propose a novel deep learning based unified cross-network solution to mitigate cold-start and data sparsity issues and provide timely recommendations for new and existing users.Furthermore, we consider the ranking problem under implicit feedback as a classification task, and propose a generic personalized listwise optimization criterion for implicit data to effectively rank a list of items. We illustrate our cross-network model using Twitter auxiliary information for recommendations on YouTube target network. Extensive comparisons against multiple time aware and cross-network base-lines show that the proposed solution is superior in terms of accuracy, novelty and diversity. Furthermore, experiments conducted on the popular MovieLens dataset suggest that the proposed listwise ranking method outperforms existing state-of-the-art ranking techniques.

Dilruk Perera, Roger Zimmermann

The overwhelming volume and complexity of information in online applications make recommendation essential for users to find information of interest. However, two major limitations that coexist in real world applications (1) incomplete user profiles, and (2) the dynamic nature of user preferences continue to degrade recommender quality in aspects such as timeliness, accuracy, diversity and novelty. To address both the above limitations in a single solution, we propose a novel cross-network time aware recommender solution. The solution first learns historical user models in the target network by aggregating user preferences from multiple source networks. Second, user level time aware latent factors are learnt to develop current user models from the historical models and conduct timely recommendations. We illustrate our solution by using auxiliary information from the Twitter source network to improve recommendations for the YouTube target network. Experiments conducted using multiple time aware and cross-network baselines under different time granularities show that the proposed solution achieves superior performance in terms of accuracy, novelty and diversity.

Dilruk Perera, Roger Zimmermann

Cross-network recommender systems use auxiliary information from multiple source networks to create holistic user profiles and improve recommendations in a target network. However, we find two major limitations in existing cross-network solutions that reduce overall recommender performance. Existing models (1) fail to capture complex non-linear relationships in user interactions, and (2) are designed for offline settings hence, not updated online with incoming interactions to capture the dynamics in the recommender environment. We propose a novel multi-layered Long Short-Term Memory (LSTM) network based online solution to mitigate these issues. The proposed model contains three main extensions to the standard LSTM: First, an attention gated mechanism to capture long-term user preference changes. Second, a higher order interaction layer to alleviate data sparsity. Third, time aware LSTM cell gates to capture irregular time intervals between user interactions. We illustrate our solution using auxiliary information from Twitter and Google Plus to improve recommendations on YouTube. Extensive experiments show that the proposed model consistently outperforms state-of-the-art in terms of accuracy, diversity and novelty.

Dilruk Perera, Roger Zimmermann

A major drawback of cross-network recommender solutions is that they can only be applied to users that are overlapped across networks. Thus, the non-overlapped users, which form the majority of users are ignored. As a solution, we propose CnGAN, a novel multi-task learning based, encoder-GAN-recommender architecture. The proposed model synthetically generates source network user preferences for non-overlapped users by learning the mapping from target to source network preference manifolds. The resultant user preferences are used in a Siamese network based neural recommender architecture. Furthermore, we propose a novel user based pairwise loss function for recommendations using implicit interactions to better guide the generation process in the multi-task learning environment.We illustrate our solution by generating user preferences on the Twitter source network for recommendations on the YouTube target network. Extensive experiments show that the generated preferences can be used to improve recommendations for non-overlapped users. The resultant recommendations achieve superior performance compared to the state-of-the-art cross-network recommender solutions in terms of accuracy, novelty and diversity.