%0 Journal Article %J BMC Family Practice %D 2015 %T Evidence-based rules from family practice to inform family practice; the learning healthcare system case study on urinary tract infections %A Soler, JK %A Corrigan, D %A Kazienko, P %A Kajdanowicz, T %A Roxana Danger %K international classification of primary care; Diagnosis; Reason for encounter; Urinary tract infection; Pyelonephritis; Transform; Transition project; Electronic patient record %K Learning healthcare system; Data-mining %X Background: Analysis of encounter data relevant to the diagnostic process sourced from routine electronic medical record (EMR) databases represents a classic example of the concept of a learning healthcare system (LHS). By collecting International Classification of Primary Care (ICPC) coded EMR data as part of the Transition Project from Dutch and Maltese databases (using the EMR TransHIS), data mining algorithms can empirically quantify the relationships of all presenting reasons for encounter (RfEs) and recorded diagnostic outcomes. We have specifically looked at new episodes of care (EoC) for two urinary system infections: simple urinary tract infection (UTI, ICPC code: U71) and pyelonephritis (ICPC code: U70). Methods: Participating family doctors (FDs) recorded details of all their patient contacts in an EoC structure using the ICPC, including RfEs presented by the patient, and the FDs’ diagnostic labels. The relationships between RfEs and episode titles were studied using probabilistic and data mining methods as part of the TRANSFoRm project. Results: The Dutch data indicated that the presence of RfE’s “Cystitis/Urinary Tract Infection”, “Dysuria”, “Fear of UTI”, “Urinary frequency/urgency”, “Haematuria”, “Urine symptom/complaint, other” are all strong, reliable, predictors for the diagnosis “Cystitis/Urinary Tract Infection” . The Maltese data indicated that the presence of RfE’s “Dysuria”, “Urinary frequency/urgency”, “Haematuria” are all strong, reliable, predictors for the diagnosis “Cystitis/Urinary Tract Infection”. The Dutch data indicated that the presence of RfE’s “Flank/axilla symptom/complaint”, “Dysuria”, “Fever”, “Cystitis/ Urinary Tract Infection”, “Abdominal pain/cramps general” are all strong, reliable, predictors for the diagnosis “Pyelonephritis” . The Maltese data set did not present any clinically and statistically significant predictors for pyelonephritis. Conclusions: We describe clinically and statistically significant diagnostic associations observed between UTIs and pyelonephritis presenting as a new problem in family practice, and all associated RfEs, and demonstrate that the significant diagnostic cues obtained are consistent with the literature. We conclude that it is possible to generate clinically meaningful diagnostic evidence from electronic sources of patient data. %B BMC Family Practice %V 16 %8 05/2015 %G eng %U http://www.biomedcentral.com/1471-2296/16/63 %N 63 %R 10.1186/s12875-015-0271-4 %0 Generic %D 2013 %T Data Mining Primary Care Data as part of the TRANSFoRm Project. European General Practice Research Network Conference in Malta on 19th October 2013 %A Kazienko, P %A Kajdanowicz, T %A Mercaderes, RA %A Curcin, V %A Soler, JK %A Corrigan, D %A Delaney, B %G eng %U http://www.hrbcentreprimarycare.ie/ppt/EPGRN Data Mining Presentation Derek Corrigan.pdf %0 Conference Paper %B Hybrid Artificial Intelligent Systems %D 2013 %T Classification Method for Differential Diagnosis Based on the Course of Episode of Care %A Popiel, A %A Kajdanowicz, T %A Kazienko, P %A Soler, JK %A Corrigan, D %A Curcin, V %A Mercaderes, RA %A Delaney, B %K Classification %K Differential Diagnosis Classification %K Episode of Care Diagnosis %X Abstract The main goal of the paper is to purpose a classification method for differential diagnosis in primary care domain. Commonly, the final diagnosis for the episode of care is related with the initial reason for encounter (RfE). However, many distinct diagnosis can follow from a single RfE and they need to be distinguished. The new method exploits the data about whole episodes of care quantified by individual patients' encounters and it extracts episode features from electronic health record to learn the classifier. The experimental studies carried out on two primary care datasets from Malta and the Netherlands for three distinct diagnosis groups revealed the validity of the proposed approach. %B Hybrid Artificial Intelligent Systems %V 8073 %P 112-121 %G eng %U http://link.springer.com/chapter/10.1007%2F978-3-642-40846-5_12 %& 2 %0 Book %D 2014 %T A methodology for mining clinical data: experiences from TRANSFoRm project. Studies in health technology and informatics %A Corrigan, D %A Soler, JK %A Kazienko, P %A Kajdanowicz, T %A Majeed, A %A Curcin, V %X Data mining of electronic health records (eHRs) allows us to identify patterns of patient data that characterize diseases and their progress and learn best practices for treatment and diagnosis. Clinical Prediction Rules (CPRs) are a form of clinical evidence that quantifies the contribution of different clinical data to a particular clinical outcome and help clinicians to decide the diagnosis, prognosis or therapeutic conduct for any given patient. The TRANSFoRm diagnostic support system (DSS) is based on the construction of an ontological repository of CPRs for diagnosis prediction in which clinical evidence is expressed using a unified vocabulary. This paper explains the proposed methodology for constructing this CPR repository, addressing algorithms and quality measures for filtering relevant rules. Some preliminary application results are also presented. %I IOS Press Ebook %V 210 %P 85-89 %G eng %U http://ebooks.iospress.nl/volumearticle/39301 %R 10.3233/978-1-61499-512-8-85