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.
15 January 2013 in Journal of the American Veterinary Medical Association
Objective—To analyze survival time and identify prognostic factors associated with outcome following discharge in dogs with primary brain tumors treated palliatively. Design—Prospective case series. Animals—51 dogs with 5 histopathologic types of brain tumors. Procedures—Owners with dogs examined from 2004 to 2008 were invited to participate if dogs had CT or MRI evidence of a brain mass that was histopathologically confirmed as a neoplasm upon death, dogs survived for ≥ 48 hours after hospital discharge, and treatments following discharge were limited to administration of prednisone or phenobarbital. Prognostic factors, including signalment, clinical signs (including duration), tumor type, tumor location, degree of peritumoral edema, lesion burden, and prescribed treatment, were evaluated. Survival time was estimated and animal- and tumor-specific variables evaluated as potential prognostic factors. Results—The median survival time in all dogs was 69 days (95% confidence interval [CI], 18 to 201 days). Multivariate analyses identified neuroanatomic location as the only significant prognostic variable, with the survival time of dogs with infratentorial tumors (n = 18) being significantly shorter (median, 28 days; 95% CI, 19 to 68 days) than survival time of dogs with supratentorial (33) tumors (median, 178 days; 95% CI, 119 to 270 days). Seizures were the most common clinical sign associated with supratentorial tumors (24/33 [73%]) and central vestibular dysfunction with infratentorial tumors (12/18). Conclusions and Clinical Relevance—Dogs with palliatively treated primary brain tumors, particularly those with tumors in the cerebellum, pons, or medulla, had a poor prognosis. However, dogs with supratentorial tumors had survival times > 3 months.
15 October 2017 in Journal of Veterinary Diagnostic Investigation
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.