Examining the factor structure, reliability, and validity of the main outcome measure used in mentalization-based therapy skills training.

BACKGROUND AND AIMS: Multiple national guidelines stress the importance for clinicians to possess good therapeutic skills for working with patients with significant relational difficulties (who may receive a diagnosis of personality disorder). Training clinicians in mentalization-based treatment skills (MBT-S) is one approach to address this. The main outcome measure used in MBT-S studies is the Knowledge and Application of MBT Questionnaire (KAMQ). However, an absence of research into the properties and validity of the KAMQ has limited the methodological quality of MBT-S evaluations so far. The aim of this study was therefore to investigate the factor structure, internal consistency, reliability, and validity of the KAMQ. METHODS: Using an existing multiprofessional sample of 217 clinicians from 2014 to 2016, we undertook exploratory factor analysis to determine the factor structure and internal consistency of the KAMQ. Convergent validity of the measure with the Attitudes to Personality Disorder Questionnaire (APDQ) was assessed in a subset of this dataset where both questionnaires had been administered (n = 92). Additionally, by recruiting a new sample of 70 clinicians, we assessed the measure's test-retest reliability. RESULTS: Factor analysis found three factors underlying 17 of the 20 KAMQ items, relating to therapeutic skills in mentalizing, beliefs about applying MBT in practice, and specific MBT knowledge. The KAMQ was revised following the factor analysis to form the KAMQ-2 with 17 items. Internal consistency (α = .85, 95% confidence interval [CI] = 0.80-0.89) and test-retest reliability (ICC = 0.84, 95% CI = 0.73-0.91) were good. In correlation analyses, the KAMQ-2 showed convergent validity with the main factor from the APDQ (n = 48; r s = 0.39, P < .01). CONCLUSION: The KAMQ-2 provides a short, reliable self-report instrument which probes clinicians' knowledge about mentalizing skills, and beliefs about using these. There was preliminary evidence for validity. The properties of the KAMQ-2 mean that more robust evaluation and development of MBT-S is now possible.

Coding and classifying GP data: the POLAR project.

BACKGROUND: Data, particularly 'big' data are increasingly being used for research in health. Using data from electronic medical records optimally requires coded data, but not all systems produce coded data. OBJECTIVE: To design a suitable, accurate method for converting large volumes of narrative diagnoses from Australian general practice records to codify them into SNOMED-CT-AU. Such codification will make them clinically useful for aggregation for population health and research purposes. METHOD: The developed method consisted of using natural language processing to automatically code the texts, followed by a manual process to correct codes and subsequent natural language processing re-computation. These steps were repeated for four iterations until 95% of the records were coded. The coded data were then aggregated into classes considered to be useful for population health analytics. RESULTS: Coding the data effectively covered 95% of the corpus. Problems with the use of SNOMED CT-AU were identified and protocols for creating consistent coding were created. These protocols can be used to guide further development of SNOMED CT-AU (SCT). The coded values will be immensely useful for the development of population health analytics for Australia, and the lessons learnt applicable elsewhere.

Clinical Safety Incident Taxonomy Performance on C4.5 Decision Tree and Random Forest.

The paper applies an artificial intelligence centered method to classify 12 clinical safety incident (CSI) classes. The paper aims to establish a taxonomy that classifies the CSI reports into their correct classes automatically and with high accuracy. The study investigates feasibility of applying the C4.5 decision tree (DT) classifier and the random forest (RF) classifier for this purpose. The classifiers were trained using randomly selected 3600 CSIs from an Incident Information Management System (IIMS) used by seven hospitals. The taxonomies investigated were the Generic Reference Model (GRM) and the World Health Organization (WHO) patient safety classification. The classifiers trained 13 GRM CSI classes and 9 WHO CSI classes using a bag-of-words approach. The overall taxonomies performance on the RF classifier was better than on the DT classifier. The performance achieved by the classifier applying the WHO taxonomy was better than the GRM taxonomy. Four of the five poorly performing classes in the GRM taxonomy significantly improved their performance on changing the taxonomy. To improve the WHO taxonomy performance the improved WHO (WHO-I) taxonomy was built by adding a new class that did not exist in WHO but existed in GRM. The performance of the RF classifier applied to the WHO-I taxonomy further improved.

POLAR Diversion: Using General Practice Data to Calculate Risk of Emergency Department Presentation at the Time of Consultation.

OBJECTIVE: This project examined and produced a general practice (GP) based decision support tool (DST), namely POLAR Diversion, to predict a patient's risk of emergency department (ED) presentation. The tool was built using both GP/family practice and ED data, but is designed to operate on GP data alone. METHODS: GP data from 50 practices during a defined time frame were linked with three local EDs. Linked data and data mapping were used to develop a machine learning DST to determine a range of variables that, in combination, led to predictive patient ED presentation risk scores. Thirteen percent of the GP data was kept as a control group and used to validate the tool. RESULTS: The algorithm performed best in predicting the risk of attending ED within the 30-day time category, and also in the no ED attendance tests, suggesting few false positives. At 0 to 30 days the positive predictive value (PPV) was 74%, with a sensitivity/recall of 68%. Non-ED attendance had a PPV of 82% and sensitivity/recall of 96%. CONCLUSION: Findings indicate that the POLAR Diversion algorithm performed better than previously developed tools, particularly in the 0 to 30 day time category. Its utility increases because of it being based on the data within the GP system alone, with the ability to create real-time "in consultation" warnings. The tool will be deployed across GPs in Australia, allowing us to assess the clinical utility, and data quality needs in further iterations.

Complex analyses on clinical information systems using restricted natural language querying to resolve time-event dependencies.

PURPOSE: This paper reports on a generic framework to provide clinicians with the ability to conduct complex analyses on elaborate research topics using cascaded queries to resolve internal time-event dependencies in the research questions, as an extension to the proposed Clinical Data Analytics Language (CliniDAL). METHODS: A cascaded query model is proposed to resolve internal time-event dependencies in the queries which can have up to five levels of criteria starting with a query to define subjects to be admitted into a study, followed by a query to define the time span of the experiment. Three more cascaded queries can be required to define control groups, control variables and output variables which all together simulate a real scientific experiment. According to the complexity of the research questions, the cascaded query model has the flexibility of merging some lower level queries for simple research questions or adding a nested query to each level to compose more complex queries. Three different scenarios (one of them contains two studies) are described and used for evaluation of the proposed solution. RESULTS: CliniDAL's complex analyses solution enables answering complex queries with time-event dependencies at most in a few hours which manually would take many days. CONCLUSION: An evaluation of results of the research studies based on the comparison between CliniDAL and SQL solutions reveals high usability and efficiency of CliniDAL's solution.

Incidence of spinal epidural lipomatosis in patients with spinal stenosis.

INRODUCTION: Spinal Epidural Lipomatosis (SEL) is believed to be a rare disorder. The incidence and prevalence of clinically symptomatic SEL in patients with spinal stenosis has never been reported in the literature. Our study aims to determine the prevalence, incidence, and associated risk factors of SEL in patients with the diagnosis of spinal stenosis. METHODS: This is a retrospective study. We reviewed the charts of 831 patients with the diagnosis of spinal stenosis over a 30 month period. All patients had spinal MRIs. Grading of SEL was performed using the Borré method. RESULTS: 52 patients (21 female and 31 male) had symptomatic moderate and severe SEL. We found a prevalence of 6.26% and an annual incidence of 2.5%. SEL was most commonly seen at L5-S1 level. 27% had received corticosteroids. All SEL patients were overweight and 79% were obese. CONCLUSIONS: SEL is not uncommon in patients with spinal stenosis. SEL should be considered as a possible diagnosis in those with symptoms of spinal stenosis especially in those with associated risk factors.

The Impact of an Enterprise Electronic Medical Record (EEMR) Model vs a Clinical Information System (CIS) Model on Usability, Efficiency, and Adaptability.

This paper describes a methodology that engages the clinical community into the design process of creating Clinical Information Systems (CISs) under a Clinical Team-Led Design (CTLD) approach in the context of using Immediately Adaptable (IA) system development technology. The methodology is contrasted against the Enterprise Electronic Medical Record (EEMR) model for usability, efficiency, and adaptability. The methodology was tested in a Breast Cancer setting where the CIS went through 4 rapid agile stages. Time and motion statistics, training times, system changes, and user feedback data was collected for assessment. The results showed that the Breast CIS increased time efficiency by 30% in the first 3 months of implementation. Users reported high usability and trainability of the system. Over 95% of system design change requests were satisfied with an average turn-around time of 3 days. The results show that systems designed under a CTLD approach, accompanied by Immediately Adaptable system architecture, provide greater efficiency for staff in clinical settings while enabling the workflow processes to be adapted dynamically as part of continuous process improvement.

Using Patient Flow Information to Determine Risk of Hospital Presentation: Protocol for a Proof-of-Concept Study.

BACKGROUND: Every day, patients are admitted to the hospital with conditions that could have been effectively managed in the primary care sector. These admissions are expensive and in many cases are possible to avoid if early intervention occurs. General practitioners are in the best position to identify those at risk of imminent hospital presentation and admission; however, it is not always possible for all the factors to be considered. A lack of shared information contributes significantly to the challenge of understanding a patient's full medical history. Some health care systems around the world use algorithms to analyze patient data in order to predict events such as emergency presentation; however, those responsible for the design and use of such systems readily admit that the algorithms can only be used to assess the populations used to design the algorithm in the first place. The United Kingdom health care system has contributed data toward algorithm development, which is possible through the unified health care system in place there. The lack of unified patient records in Australia has made building an algorithm for local use a significant challenge. OBJECTIVE: Our objective is to use linked patient records to track patient flow through primary and secondary health care in order to develop a tool that can be applied in real time at the general practice level. This algorithm will allow the generation of reports for general practitioners that indicate the relative risk of patients presenting to an emergency department. METHODS: A previously designed tool was used to deidentify the general practice and hospital records of approximately 100,000 patients. Records were pooled for patients who had attended emergency departments within the Eastern Health Network of hospitals and general practices within the Eastern Health Network catchment. The next phase will involve development of a model using a predictive analytic machine learning algorithm. The model will be developed iteratively, testing the combination of variables that will provide the best predictive model. RESULTS: Records of approximately 97,000 patients who have attended both a general practice and an emergency department have been identified within the database. These records are currently being used to develop the predictive model. CONCLUSIONS: Records from general practice and emergency department visits have been identified and pooled for development of the algorithm. The next phase in the project will see validation and live testing of the algorithm in a practice setting. The algorithm will underpin a clinical decision support tool for general practitioners which will be tested for face validity in this initial study into its efficacy.

Variation in the limit-of-detection of the ProSpecT Campylobacter microplate enzyme immunoassay in stools spiked with emerging Campylobacter species.

Campylobacter enteritis in humans is primarily associated with C. jejuni/coli infection. The impact of other Campylobacter spp. is likely to be underestimated due to the bias of culture methods towards Campylobacter jejuni/coli diagnosis. Stool antigen tests are becoming increasingly popular and appear generally less species-specific. A review of independent studies of the ProSpecT® Campylobacter Microplate enzyme immunoassay (EIA) developed for C. jejuni/coli showed comparable diagnostic results to culture methods but the examination of non-jejuni/coli Campylobacter spp. was limited and the limit-of-detection (LOD), where reported, varied between studies. This study investigated LOD of EIA for Campylobacter upsaliensis, Campylobacter hyointestinalis and Campylobacter helveticus spiked in human stools. Multiple stools and Campylobacter isolates were used in three different concentrations (10(4)-10(9)CFU/ml) to reflect sample heterogeneity. All Campylobacter species evaluated were detectable by EIA. Multivariate analysis showed LOD varied between Campylobacter spp. and faecal consistency as fixed effects and individual faecal samples as random effects. EIA showed excellent performance in replicate testing for both within and between batches of reagents, in agreement between visual and spectrophotometric reading of results, and returned no discordance between the bacterial concentrations within independent dilution test runs (positive results with lower but not higher concentrations). This study shows how limitations in experimental procedures lead to an overestimation of consistency and uniformity of LOD for EIA that may not hold under routine use in diagnostic laboratories. Benefits and limitations for clinical practice and the influence on estimates of performance characteristics from detection of multiple Campylobacter spp. by EIA are discussed.

A pilot before-and-after study of a brief teaching programme for psychiatry trainees in mentalizing skills.

BACKGROUND AND AIMS: Negative attitudes in clinicians towards people with personality disorder are common and associated with poor care. National guidelines recommend developing interventions to improve attitudes. Mentalization-based treatment theory and techniques provide a plausible intervention. We therefore evaluated the effect of teaching mentalizing skills on clinicians' attitudes towards personality disorder. METHODS: Pilot before-and-after study of trainee psychiatrists receiving four teaching sessions in mentalizing skills. Self-report questionnaires were completed at baseline and post teaching programme. MAIN OUTCOME MEASURE: Attitudes to Personality Disorder Questionnaire. SECONDARY MEASURE: Knowledge and Application of Mentalization-based treatment Questionnaire. RESULTS: Sixteen doctors were recruited with no study drop-out. Mean Attitudes to Personality Disorder Questionnaire score was superior post teaching programme versus baseline (135.3 vs. 124.5, standardised mean difference = 0.72, 95% confidence interval = 0.01 to 1.44). Mean Knowledge and Application of Mentalization-based treatment Questionnaire score was superior post teaching programme versus baseline (112.5 vs. 97.1, standardised mean difference = 1.83, 95% confidence interval 0.98 to 2.67). CONCLUSIONS: As expected from a pilot study, the estimate of effect is imprecise. Within this limitation, our findings suggest that teaching in mentalizing skills improved attitudes and mentalization-based treatment knowledge to a clinically relevant degree. This has important implications for patient outcomes and staff development. Our study paves the way for a full-scale study to provide more precise and robust evidence.

Automated Classification of Clinical Incident Types.

We consider the task of automatic classification of clinical incident reports using machine learning methods. Our data consists of 5448 clinical incident reports collected from the Incident Information Management System used by 7 hospitals in the state of New South Wales in Australia. We evaluate the performance of four classification algorithms: decision tree, naïve Bayes, multinomial naïve Bayes and support vector machine. We initially consider 13 classes (incident types) that were then reduced to 12, and show that it is possible to build accurate classifiers. The most accurate classifier was the multinomial naïve Bayes achieving accuracy of 80.44% and AUC of 0.91. We also investigate the effect of class labelling by an ordinary clinician and an expert, and show that when the data is labelled by an expert the classification performance of all classifiers improves. We found that again the best classifier was multinomial naïve Bayes achieving accuracy of 81.32% and AUC of 0.97. Our results show that some classes in the Incident Information Management System such as Primary Care are not distinct and their removal can improve performance; some other classes such as Aggression Victim are easier to classify than others such as Behavior and Human Performance. In summary, we show that the classification performance can be improved by expert class labelling of the training data, removing classes that are not well defined and selecting appropriate machine learning classifiers.

Automatic negation detection in narrative pathology reports.

OBJECTIVE: To detect negations of medical entities in free-text pathology reports with different approaches, and evaluate their performances. METHODS AND MATERIAL: Three different approaches were applied for negation detection: the lexicon-based approach was a rule-based method, relying on trigger terms and termination clues; the syntax-based approach was also a rule-based method, where the rules and negation patterns were designed using the dependency output from the Stanford parser; the machine-learning-based approach used a support vector machine as a classifier to build models with a number of features. A total of 284 English pathology reports of lymphoma were used for the study. RESULTS: The machine-learning-based approach had the best overall performance on the test set with micro-averaged F-score of 82.56%, while the syntax-based approach performed worst with 78.62% F-score. The lexicon-based approach attained an overall average precision of 89.74% and recall of 76.09%, which were significantly better than the results achieved by Negation Tagger with a similar approach. DISCUSSION: The lexicon-based approach benefitted from being customized to the corpus more than the other two methods. The errors in negation detection with the syntax-based approach producing poorest performance were mainly due to the poor parsing results, and the errors with the other methods were probably because of the abnormal grammatical structures. CONCLUSIONS: A machine-learning-based approach has potential advantages for negation detection, and may be preferable for the task. To improve the overall performance, one of the possible solutions is to apply different approaches to each section in the reports.

Efficiency achievements from a user-developed real-time modifiable clinical information system.

STUDY OBJECTIVE: This investigation was initiated after the introduction of a new information system into the Nepean Hospital Emergency Department. A retrospective study determined that the problems introduced by the new system led to reduced efficiency of the clinical staff, demonstrated by deterioration in the emergency department's (ED's) performance. This article is an investigation of methods to improve the design and implementation of clinical information systems for an ED by using a process of clinical team-led design and a technology built on a radically new philosophy denoted as emergent clinical information systems. METHODS: The specific objectives were to construct a system, the Nepean Emergency Department Information Management System (NEDIMS), using a combination of new design methods; determine whether it provided any reduction in time and click burden on the user in comparison to an enterprise proprietary system, Cerner FirstNet; and design and evaluate a model of the effect that any reduction had on patient throughput in the department. RESULTS: The methodology for conducting a direct comparison between the 2 systems used the 6 activity centers in the ED of clerking, triage, nursing assessments, fast track, acute care, and nurse unit manager. A quantitative study involved the 2 systems being measured for their efficiency on 17 tasks taken from the activity centers. A total of 332 task instances were measured for duration and number of mouse clicks in live usage on Cerner FirstNet and in reproduction of the same Cerner FirstNet work on NEDIMS as an off-line system. The results showed that NEDIMS is at least 41% more efficient than Cerner FirstNet (95% confidence interval 21.6% to 59.8%). In some cases, the NEDIMS tasks were remodeled to demonstrate the value of feedback to create improvements and the speed and economy of design revision in the emergent clinical information systems approach. The cost of the effort in remodeling the designs showed that the time spent on remodeling is recovered within a few days in time savings to clinicians. An analysis of the differences between Cerner FirstNet and NEDIMS for sequences of patient journeys showed an average difference of 127 seconds and 15.2 clicks. A simulation model of workflows for typical patient journeys for a normal daily attendance of 165 patients showed that NEDIMS saved 23.9 hours of staff time per day compared with Cerner FirstNet. CONCLUSION: The results of this investigation show that information systems that are designed by a clinical team using a technology that enables real-time adaptation provides much greater efficiency for the ED. Staff consider that a point-and-click user interface constantly interrupts their train of thought in a way that does not happen when writing on paper. This is partially overcome by the reduction of cognitive load that arises from minimizing the number of clicks to complete a task in the context of global versus local workflow optimization.

Restricted natural language based querying of clinical databases.

PURPOSE: To elevate the level of care to the community it is essential to provide usable tools for healthcare professionals to extract knowledge from clinical data. In this paper a generic translation algorithm is proposed to translate a restricted natural language query (RNLQ) to a standard query language like SQL (Structured Query Language). METHODS: A special purpose clinical data analytics language (CliniDAL) has been introduced which provides scheme of six classes of clinical questioning templates. A translation algorithm is proposed to translate the RNLQ of users to SQL queries based on a similarity-based Top-k algorithm which is used in the mapping process of CliniDAL. Also a two layer rule-based method is used to interpret the temporal expressions of the query, based on the proposed temporal model. The mapping and translation algorithms are generic and thus able to work with clinical databases in three data design models, including Entity-Relationship (ER), Entity-Attribute-Value (EAV) and XML, however it is only implemented for ER and EAV design models in the current work. RESULTS: It is easy to compose a RNLQ via CliniDAL's interface in which query terms are automatically mapped to the underlying data models of a Clinical Information System (CIS) with an accuracy of more than 84% and the temporal expressions of the query comprising absolute times, relative times or relative events can be automatically mapped to time entities of the underlying CIS and to normalized temporal comparative values. CONCLUSION: The proposed solution of CliniDAL using the generic mapping and translation algorithms which is enhanced by a temporal analyzer component provides a simple mechanism for composing RNLQ for extracting knowledge from CISs with different data design models for analytics purposes.

Supervised machine learning and active learning in classification of radiology reports.

OBJECTIVE: This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry. MATERIALS AND METHODS: In addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney). RESULTS: The reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry's held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL. DISCUSSION: AL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly. CONCLUSIONS: The most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries.

Mapping query terms to data and schema using content based similarity search in clinical information systems.

This paper reports on the issues in mapping the terms of a query to the field names of the schema of an Entity Relationship (ER) model or to the data part of the Entity Attribute Value (EAV) model using similarity based Top-K algorithm in clinical information system together with an extension of EAV mapping for medication names. In addition, the details of the mapping algorithm and the required pre-processing including NLP (Natural Language Processing) tasks to prepare resources for mapping are explained. The experimental results on an example clinical information system demonstrate more than 84 per cent of accuracy in mapping. The results will be integrated into our proposed Clinical Data Analytics Language (CliniDAL) to automate mapping process in CliniDAL.

A temporal model for Clinical Data Analytics language.

The proposal of a special purpose language for Clinical Data Analytics (CliniDAL) is presented along with a general model for expressing temporal events in the language. The temporal dimension of clinical data needs to be addressed from at least five different points of view. Firstly, how to attach the knowledge of time based constraints to queries; secondly, how to mine temporal data in different CISs with various data models; thirdly, how to deal with both relative time and absolute time in the query language; fourthly, how to tackle internal time-event dependencies in queries, and finally, how to manage historical time events preserved in the patient's narrative. The temporal elements of the language are defined in Bachus Naur Form (BNF) along with a UML schema. Its use in a designed taxonomy of a five class hierarchy of data analytics tasks shows the solution to problems of time event dependencies in a highly complex cascade of queries needed to evaluate scientific experiments. The issues in using the model in a practical way are discussed as well.

Automated validation of patient safety clinical incident classification: macro analysis.

Patient safety is the buzz word in healthcare. Incident Information Management System (IIMS) is electronic software that stores clinical mishaps narratives in places where patients are treated. It is estimated that in one state alone over one million electronic text documents are available in IIMS. In this paper we investigate the data density available in the fields entered to notify an incident and the validity of the built in classification used by clinician to categories the incidents. Waikato Environment for Knowledge Analysis (WEKA) software was used to test the classes. Four statistical classifier based on J48, Naïve Bayes (NB), Naïve Bayes Multinominal (NBM) and Support Vector Machine using radial basis function (SVM_RBF) algorithms were used to validate the classes. The data pool was 10,000 clinical incidents drawn from 7 hospitals in one state in Australia. In first part of the study 1000 clinical incidents were selected to determine type and number of fields worth investigating and in the second part another 5448 clinical incidents were randomly selected to validate 13 clinical incident types. Result shows 74.6% of the cells were empty and only 23 fields had content over 70% of the time. The percentage correctly classified classes on four algorithms using categorical dataset ranged from 42 to 49%, using free-text datasets from 65% to 77% and using both datasets from 72% to 79%. Kappa statistic ranged from 0.36 to 0.4. for categorical data, from 0.61 to 0.74. for free-text and from 0.67 to 0.77 for both datasets. Similar increases in performance in the 3 experiments was noted on true positive rate, precision, F-measure and area under curve (AUC) of receiver operating characteristics (ROC) scores. The study demonstrates only 14 of 73 fields in IIMS have data that is usable for machine learning experiments. Irrespective of the type of algorithms used when all datasets are used performance was better. Classifier NBM showed best performance. We think the classifier can be improved further by reclassifying the most confused classes and there is scope to apply text mining tool on patient safety classifications.

Using NLP to identify cancer cases in imaging reports drawn from radiology information systems.

A Natural Language processing (NLP) classifier has been developed for the Victorian and NSW Cancer Registries with the purpose of automatically identifying cancer reports from imaging services, transmitting them to the Registries and then extracting pertinent cancer information. Large scale trials conducted on over 40,000 reports show the sensitivity for identifying reportable cancer reports is above 98% with a specificity above 96%. Detection of tumour stream, report purpose, and a variety of extracted content is generally above 90% specificity. The differences between report layout and authoring strategies across imaging services appear to require different classifiers to retain this high level of accuracy. Linkage of the imaging data with existing registry records (hospital and pathology reports) to derive stage and recurrence of cancer has commenced and shown very promising results.