KConnect

The Problem

The healthcare sector consists of many stakeholders, including the pharmaceutical and medical products industries, healthcare providers, health insurers, clinicians and patients. Each stakeholder generates pools of textual data, which have typically remained disconnected. The amount of information to analyse in the health sector is growing rapidly. The two types of textual information in the medical domain that are of particular interest in KConnect are published scientific papers in the medical domain, and Electronic Health Records (EHR). 

It is essential to process this data for Comparative Effectiveness Research to predict which treatments work best for which patients; for Predictive Modeling to flag patients with potential negative developments (e.g. potentially suicidal psychiatric patients); as well as for Quality Control of the healthcare system. As increasing numbers of medical establishments are realising the potential of EHR analysis, and also the cost of not doing this analysis in terms of inefficiency and unnecessary loss of life, the demand for such solutions will increase significantly in the next years.

Our Research

The KConnect semantic index at The South London and Maudsley NHS Foundation Trust (SLaM) will be based on a case register derived from SLaM’s full patient record. A preliminary requirement for predictive models of adverse drug events (ADEs) has been identified from ongoing work. This model would draw on literature relating to medications as well as analyses carried out within the records database (CRIS). Thus, records data will be analysed up to the point of the ADE, generating a timeline of events which will then be compared with control timelines of persons with similar characteristics who have not experienced the ADE. Predictive models from records text will then be compared with those drawn from the literature (e.g. on drug interactions) and the extent to which these improve on each other will be assessed. One example of a potential analysis relates to clozapine prescribing and whether pneumonia as an ADR is preceded by a hypersalivation, another known clozapine ADE. 


Themes
Discovery Science
Learning Health Systems
Precision Medicine

Disease: Mental Health 

People: Prof Richard Dobson, Prof Robert Stewart, Dr Honghan Wu

Collaborators: Prof Allan Hanbury, Dr Angus Roberts, Dr Ian Roberts, Dr Genevieve Gorrell

Publications

Honghan Wu, Zina M. Ibrahim, Ehtesham Iqbal and Richard JB Dobson. Predicting Adverse Events from Multiple and Dynamic Medication Episodes. Accepted by AI-2016 Thirty-sixth SGAI International Conference on Artificial Intelligence. Cambridge, England, 13-15 December 2016.

Impact in research