Automatic Classification of Free-Text Radiology Reports to Identify Limb Fractures using Machine Learning and the SNOMED CT Ontology.

OBJECTIVE: To develop and evaluate machine learning techniques that identify limb fractures and other abnormalities (e.g. dislocations) from radiology reports. MATERIALS AND METHODS: 99 free-text reports of limb radiology examinations were acquired from an Australian public hospital. Two clinicians were employed to identify fractures and abnormalities from the reports; a third senior clinician resolved disagreements. These assessors found that, of the 99 reports, 48 referred to fractures or abnormalities of limb structures. Automated methods were then used to extract features from these reports that could be useful for their automatic classification. The Naive Bayes classification algorithm and two implementations of the support vector machine algorithm were formally evaluated using cross-fold validation over the 99 reports. RESULTS: Results show that the Naive Bayes classifier accurately identifies fractures and other abnormalities from the radiology reports. These results were achieved when extracting stemmed token bigram and negation features, as well as using these features in combination with SNOMED CT concepts related to abnormalities and disorders. The latter feature has not been used in previous works that attempted classifying free-text radiology reports. DISCUSSION: Automated classification methods have proven effective at identifying fractures and other abnormalities from radiology reports (F-Measure up to 92.31%). Key to the success of these techniques are features such as stemmed token bigrams, negations, and SNOMED CT concepts associated with morphologic abnormalities and disorders. CONCLUSION: This investigation shows early promising results and future work will further validate and strengthen the proposed approaches.

Sustained reductions in emergency department laboratory test orders: impact of a simple intervention.

OBJECTIVES: To determine whether a pathology request form allowing interns and residents to order only a limited range of laboratory blood tests prior to consultation with a registrar or consultant can reduce test ordering in an emergency department (ED). METHODS: A prospective before-and-after study in an adult tertiary-referral teaching hospital ED was conducted. A pathology request form with a limited list of permissible tests was implemented for use by junior medical officers. Tests for patients 16 years and older presenting in a 20-week pre-intervention period from 19 January 2009 were compared with those in a corresponding 20-week post-intervention period from 18 January 2010. Main outcome measures were the number and cost of blood tests ordered. RESULTS: 24 652 and 25 576 presentations were analysed in the pre- and post-intervention periods, respectively. The mean number of blood tests ordered per 100 ED presentations fell by 19% from 172 in the pre- to 140 in the post-intervention period (p=0.001). The mean cost of blood tests ordered per 100 ED presentations fell by 17% from $A3177 in the pre- to $A2633 in the post-intervention period (p=0.001). There were falls in the number of coagulation profiles (11.1 vs 4.8/100 patients), C-reactive protein (5.6 vs 2.7/100 patients), erythrocyte sedimentation rate (2.5 vs 1.3/100 patients) and thyroid function tests (2.2 vs 1.6/100 patients). CONCLUSIONS: Pathology request forms limiting tests that an intern and resident may order prior to consultation with a registrar or consultant are an effective low maintenance method for reducing laboratory test ordering in the ED that is sustainable over 12 months.

Understanding requirements of novel healthcare information systems for management of advanced prostate cancer.

Effective management of chronic diseases is a global health priority. A healthcare information system offers opportunities to address challenges of chronic disease management. However, the requirements of health information systems are often not well understood. The accuracy of requirements has a direct impact on the successful design and implementation of a health information system. Our research describes methods used to understand the requirements of health information systems for advanced prostate cancer management. The research conducted a survey to identify heterogeneous sources of clinical records. Our research showed that the General Practitioner was the common source of patient's clinical records (41%) followed by the Urologist (14%) and other clinicians (14%). Our research describes a method to identify diverse data sources and proposes a novel patient journey browser prototype that integrates disparate data sources.

Identifying symptom groups from Emergency Department presenting complaint free text using SNOMED CT.

Patients presenting to Emergency Departments may be categorised into different symptom groups for the purpose of research and quality improvement. The grouping is challenging due to the variability in the way presenting complaints are recorded by clinical staff. This work proposes analysis of the presenting complaint free-text using the semantics encoded in the SNOMED CT ontology. This work demonstrates a validated prototype system that can classify unstructured free-text narratives into patient's symptom group. A rule-based mechanism was developed using variety of keywords to identify the patient's symptom group. The system was validated against the manual identification of the symptom groups by two expert clinical research nurses on 794 patient presentations from six participating hospitals. The comparison of system results with one clinical research nurse showed 99.3% sensitivity; 80.0% specificity and 0.9 F-score for identifying "chest pain" symptom group.