FST Graduate Research Topic


Research Topic: AGI Research and Development: Patient-Specific Treatment Recommender in Healthcare
Suggested By: Harris Wang
Last Update: September 28th, 2025

Constrained Object Hierarchies (COH) provide a neuroscience-inspired theoretical framework for modeling Artificial General Intelligence (AGI). As a flexible and robust foundation, COH supports the representation of general intelligent systems across diverse domains.


Formally, a COH is defined as a 9-tuple:


O = (C, A, M, N, E, I, T, G, D)


Where:



  • C: Components – sub-objects organized hierarchically

  • A: Attributes – state variables describing object properties

  • M: Methods – executable actions associated with components

  • N: Neural Components – adaptive models for learning and inference

  • E: Embedding Neural Component – semantic representation of the COH

  • I: Identity Constraints – rules ensuring object integrity

  • T: Trigger Constraints – event-condition-action rules for dynamic behavior

  • G: Goal Constraints – optimization objectives guiding intelligent behavior

  • D: Constraint Daemons – real-time monitors enforcing system constraints





Based on the COH framework, the modelling process and result of Patient-Specific Treatment Recommender in Healthcare are as follows:


System Description and Significance: This system personalizes medical treatment by integrating patient data, clinical knowledge, and outcome predictions. Its significance lies in enabling precision medicine, where treatments are tailored to individual patient characteristics rather than population averages. The system addresses the critical challenge of balancing treatment efficacy with safety considerations in complex medical decision-making.


Analysis and Design: The system must integrate diverse information sources while maintaining rigorous safety standards. Identity constraints encode fundamental medical ethics and safety protocols, while neural components enable personalization by learning from patient data and treatment outcomes. The hierarchical structure separates concerns between data management, knowledge representation, and recommendation logic.


Modelling Solution:



  • C: {PatientMedicalRecord, ClinicalGuidelines, DrugInteractionDatabase, RecommenderEngine}

  • A: patient_vitals, genomic_data, current_medications, treatment_options

  • M: query_guidelines(), check_interactions(), calculate_personalized_dose()

  • N: OutcomePredictionModel for treatment efficacy/side-effects

  • E: Embedding of patient's overall health status and disease profile

  • I: Recommended treatment must not have severe known interactions (safety_first)

  • T: IF new_lab_result indicates_toxicity THEN alert_doctor AND suggest_alternative

  • G: Maximize_treatment_efficacy AND Minimize_side_effects

  • D: SafetyDaemon cross-referencing new patient data with identity constraints


The COH formalism captures the delicate balance between personalized adaptation and safety assurance through its constraint hierarchy. The neural components enable precision medicine while the identity constraints maintain safety boundaries.





You may choose this topic and pursue one of the following routes:


📝 Essay



  • Survey existing methodologies for modeling, designing, and implementing similar intelligent systems.

  • Include:

    • Literature synthesis

    • COH framework analysis

    • Critical evaluation of competing approaches




🛠️ Project



  • Design and implement the system using the COH model.

  • Include:

    • System architecture and design

    • Development and testing

    • Demonstration of core functionality




🎓 Thesis



  • Explore COH’s theoretical foundations in depth.

  • Include:

    • Proposed enhancements or extensions

    • Implementation and evaluation

    • Development of an advanced intelligent system grounded in COH principles