Review of Medical Decision Support and Machine-Learning Methods.

Machine-learning methods can assist with the medical decision-making processes at the both the clinical and diagnostic levels. In this article, we first review historical milestones and specific applications of computer-based medical decision support tools in both veterinary and human medicine. Next, we take a mechanistic look at 3 archetypal learning algorithms-naive Bayes, decision trees, and neural network-commonly used to power these medical decision support tools. Last, we focus our discussion on the data sets used to train these algorithms and examine methods for validation, data representation, transformation, and feature selection. From this review, the reader should gain some appreciation for how these decision support tools have and can be used in medicine along with insight on their inner workings.

Duration of ß-adrenoceptor blockade associated with once-daily oral administration of atenolol in healthy dogs.

OBJECTIVE To test the hypothesis that once-daily oral administration of atenolol would attenuate the heart rate response to isoproterenol for 24 hours. ANIMALS 20 healthy dogs. PROCEDURES A double-blind randomized placebo-controlled crossover study was conducted. Dogs were assigned to receive atenolol (1 mg/kg, PO, q 24 h) or a placebo for 5 to 7 days. After a washout period of 7 days, dogs then received the other treatment. Heart rate at rest (HRr) and heart rate induced by administration of isoproterenol (HRi) as a constant rate infusion (0.2 µg/kg/min for 5 to 7 minutes) were obtained by use of ECG 0, 0.25, 3, 6, 12, 18, and 24 hours after administration of the final dose of atenolol or the placebo. A mixed-model ANOVA was used to evaluate effects of treatment, time after drug or placebo administration, treatment-by-time interaction, period, and sequence on HRr and HRi. RESULTS Effects of sequence or period were not detected. There was a significant effect of treatment and the treatment-by-time interaction on HRi. Atenolol significantly attenuated HRi for 24 hours but did so maximally at 3 hours (least squares mean ± SE, 146 ± 5 beats/min and 208 ± 5 beats/min for atenolol and placebo, respectively). The effect at 24 hours was small (193 ± 5 beats/min and 206 ± 5 beats/min for atenolol and placebo, respectively). Atenolol had a small but significant effect on HRr. CONCLUSIONS AND CLINICAL RELEVANCE This study of healthy dogs receiving atenolol supported a recommendation for a dosing interval < 24 hours.

Identifying free-text features to improve automated classification of structured histopathology reports for feline small intestinal disease.

The histologic evaluation of gastrointestinal (GI) biopsies is the standard for diagnosis of a variety of GI diseases (e.g., inflammatory bowel disease [IBD] and alimentary lymphoma [ALA]). The World Small Animal Veterinary Association (WSAVA) Gastrointestinal International Standardization Group proposed a reporting standard for GI biopsies consisting of a defined set of microscopic features. We compared the machine classification accuracy of free-text microscopic findings with those represented in the WSAVA format with a diagnosis of IBD and ALA. Unstructured free-text duodenal biopsy pathology reports from cats ( n = 60) with a diagnosis of IBD ( n = 20), ALA ( n = 20), or normal ( n = 20) were identified. Biopsy samples from these cases were then scored following the WSAVA guidelines to create a set of structured reports. Three supervised machine-learning algorithms were trained using the structured and then the unstructured reports. Diagnosis classification accuracy for the 3 algorithms was compared using the structured and unstructured reports. Using naive Bayes and neural networks, unstructured information-based models achieved higher diagnostic accuracy (0.90 and 0.88, respectively) compared to the structured information-based models (0.74 and 0.72, respectively). Results suggest that discriminating diagnostic information was lost using current WSAVA microscopic guideline features. Addition of free-text features (number of plasma cells) increased WSAVA auto-classification performance. The methodologies reported in our study represent a way of identifying candidate microscopic features for use in structured histopathology reports.

A review of medical terminology standards and structured reporting.

Much effort has been invested in standardizing medical terminology for representation of medical knowledge, storage in electronic medical records, retrieval, reuse for evidence-based decision making, and for efficient messaging between users. We only focus on those efforts related to the representation of clinical medical knowledge required for capturing diagnoses and findings from a wide range of general to specialty clinical perspectives (e.g., internists to pathologists). Standardized medical terminology and the usage of structured reporting have been shown to improve the usage of medical information in secondary activities, such as research, public health, and case studies. The impact of standardization and structured reporting is not limited to secondary activities; standardization has been shown to have a direct impact on patient healthcare.

Evaluation of supervised machine-learning algorithms to distinguish between inflammatory bowel disease and alimentary lymphoma in cats.

Inflammatory bowel disease (IBD) and alimentary lymphoma (ALA) are common gastrointestinal diseases in cats. The very similar clinical signs and histopathologic features of these diseases make the distinction between them diagnostically challenging. We tested the use of supervised machine-learning algorithms to differentiate between the 2 diseases using data generated from noninvasive diagnostic tests. Three prediction models were developed using 3 machine-learning algorithms: naive Bayes, decision trees, and artificial neural networks. The models were trained and tested on data from complete blood count (CBC) and serum chemistry (SC) results for the following 3 groups of client-owned cats: normal, inflammatory bowel disease (IBD), or alimentary lymphoma (ALA). Naive Bayes and artificial neural networks achieved higher classification accuracy (sensitivities of 70.8% and 69.2%, respectively) than the decision tree algorithm (63%, p < 0.0001). The areas under the receiver-operating characteristic curve for classifying cases into the 3 categories was 83% by naive Bayes, 79% by decision tree, and 82% by artificial neural networks. Prediction models using machine learning provided a method for distinguishing between ALA-IBD, ALA-normal, and IBD-normal. The naive Bayes and artificial neural networks classifiers used 10 and 4 of the CBC and SC variables, respectively, to outperform the C4.5 decision tree, which used 5 CBC and SC variables in classifying cats into the 3 classes. These models can provide another noninvasive diagnostic tool to assist clinicians with differentiating between IBD and ALA, and between diseased and nondiseased cats.

Development and evaluation of methods for structured recording of heart murmur findings using SNOMED-CT post-coordination.

OBJECTIVE: This study evaluated an existing SNOMED-CT model for structured recording of heart murmur findings and compared it to a concept-dependent attributes model using content from SNOMED-CT. METHODS: The authors developed a model for recording heart murmur findings as an alternative to SNOMED-CT's use of Interprets and Has interpretation. A micro-nomenclature was then created to support each model using subset and extension mechanisms described for SNOMED-CT. Each micro-nomenclature included a partonomy of cardiac cycle timing values. A mechanism for handling ranges of values was also devised. One hundred clinical heart murmurs were recorded using purpose-built recording software based on both models. RESULTS: Each micro-nomenclature was extended through the addition of the same list of concepts. SNOMED role grouping was required in both models. All 100 clinical murmurs were described using each model. The only major differences between the two models were the number of relationship rows required for storage and the hierarchical assignments of concepts within the micro-nomenclatures. CONCLUSION: The authors were able to capture 100 clinical heart murmurs with both models. Requirements for implementing the two models were virtually identical. In fact, data stored using these models could be easily interconverted. There is no apparent penalty for implementing either approach.