CDT Seminar Overview Health Informatics Clinical informatics o

CDT Seminar Overview: Health Informatics

Clinical informatics o Large amount of clinical data – BIG DATA n n EHR, hospital discharge letters guidelines, protocols, etc. tests, measurements, medical literature (case notes, . . . ) o Ultimate aim: MAKING SENSE OF THIS DATA to support clinical research and facilitate clinical decision support o Close collaboration with clinical teams and pharmaceutical industry, local and wider

Health e-research centre (He. RC) New £ 18 M centre to be opened soon Datasets Link Value Science and Industry (R&D) Link Ingredients Experts Insights Data Quality Improved Care for Patients and Communities (Service) Methods

Health e-research centre (He. RC) o CS areas in need n Data management o Machine learning, data mining o Text mining n Information management o privacy preservation o User interface design o High-performance computing n Knowledge management o ontologies, logics, Bayesian modelling o reasoning

Clinical text mining o Extract data from Electronic Health Records (EHRs) o Challenges n Highly condensed text o often without proper sentences o list of medications, symptoms, acronyms, etc. n Terminological variability and ambiguity o orthographic, acronyms, local conventions n Various sections o previous history, social/family background n Recording “practice” vary o aneurism size: ‘large’, between 20 -30 mm

Patient: X Date: 12. 02. 2007. Medication: Enalapril 20 mg Duration: 7 days Frequency: 2 X 1 Mode: oral Reason: hyperthension Dg. cardiac arrest, ….

Example: extract status of diseases Uo. M performance (ranked 1 st/28) Micro-average: Accuracy (0. 9723) Macro-average: P (0. 8482), R (0. 7737), F-score (0. 8052) #Eval #Corr #Gold Precision Recall F-score Y 2267 2132 2192 0. 9404 0. 9726 0. 9562 N 56 40 65 0. 7142 0. 6153 0. 6611 Q 12 9 17 0. 7500 0. 5294 0. 6206 U 5709 5640 5770 0. 9879 0. 9774 0. 9826 Yang, H. , Spasic, I. , Keane, J. , Nenadic, G. : A Text Mining Approach to the Prediction of a Disease Status from Clinical Discharge Summaries, JAMIA 16(4): 596 -600

Clinical “narratives” very anxious dry cough feeling low no herion use

Mining health-care Web 2. 0 Sentiment mining of health-related social media n e-epidemiology n suicide prevention n quality of life assessment n. . .

He. RC research themes o Co. OP n “Coproducing observation with patients” o MOD n “Missed opportunities detector” o SEA-3 n “Scalable endotypes of asthma, allergies andrology” o DOT n Diabesity outcomes translator o FIN n Trials feasibility improvement network

Linked 2 Safety o An advanced environment for clinical research n based on clinical care information in EHRs and clinical trial systems a) early detection of patients’ safety issues b) identification of adverse events c) identification of suitable cohorts for clinical trials o Use semantic technologies (Linked Data) and data/text analytics o Inter-disciplinary at Manchester involving CS, Medicine and Mathematics http: //www. linked 2 safety-project. eu/

Clinical document management o Dynamic documentation knowledge services n find the right forms/questions depending on the patient and clinical observations o reasoning n present it to the users o Tasks/areas n Modelling (ontologies, description logics, SW) n Data analytics and integration n User interface design

Systems biology o Large-scale extraction and contextualization of biomolecular events n extraction of host-pathogen interactions n molecular modelling of thyroid cancerogenesis using text mining o Modelling dynamics of small blood vessels and roles of smooth muscle cells n combine literature mining and structured data

Contacts o Goran Nenadic n text mining, information management n e-health research o Bijan Parsia n Knowledge management, reasoning n GUI o John Keane n data management/analytics n decision support systems