Michael D. Cusimano

Chris Brogly, Saif Rjaibi, Charlotte Liang et al.

Small Language Models (SLMs) have potential to be used for automatically labelling and identifying aspects of text data for medicine/health-related purposes from documents and the web. As their resource requirements are significantly lower than Large Language Models (LLMs), these can be deployed potentially on more types of devices. SLMs often are benchmarked on health/medicine-related tasks, such as MedQA, although performance on these can vary especially depending on the size of the model in terms of number of parameters. Furthermore, these test results may not necessarily reflect real-world performance regarding the automatic labelling or identification of texts in documents and the web. As a result, we compared topic-relatedness scores from Microsofts phi-3-mini-4k-instruct SLM to the topic-relatedness scores from 7 human evaluators on 1144 samples of medical/health-related texts and 1117 samples of sports injury-related texts. These texts were from a larger dataset of about 9 million news headlines, each of which were processed and assigned scores by phi-3-mini-4k-instruct. Our sample was selected (filtered) based on 1 (low filtering) or more (high filtering) Boolean conditions on the phi-3 SLM scores. We found low-moderate significant correlations between the scores from the SLM and human evaluators for sports injury texts with low filtering (\r{ho} = 0.3413, p < 0.001) and medicine/health texts with high filtering (\r{ho} = 0.3854, p < 0.001), and low significant correlation for medicine/health texts with low filtering (\r{ho} = 0.2255, p < 0.001). There was negligible, insignificant correlation for sports injury-related texts with high filtering (\r{ho} = 0.0318, p = 0.4466).

Ashirbani Saha, Pantea Fadaiefard, Jessica E. Rabski et al.

We performed a PubMed search to find 148 papers published between January 2010 and December 2019 related to human brain, Diffusion Tensor Imaging (DTI), and Machine Learning (ML). The studies focused on healthy cohorts (n = 15), mental health disorders (n = 25), tumor (n = 19), trauma (n = 5), dementia (n = 24), developmental disorders (n = 5), movement disorders (n = 9), other neurological disorders (n = 27), miscellaneous non-neurological disorders, or without stating the disease of focus (n = 7), and multiple combinations of the aforementioned categories (n = 12). Classification of patients using information from DTI stands out to be the most commonly (n = 114) performed ML application. A significant number (n = 93) of studies used support vector machines (SVM) as the preferred choice of ML model for classification. A significant portion (31/44) of publications in the recent years (2018-2019) continued to use SVM, support vector regression, and random forest which are a part of traditional ML. Though many types of applications across various health conditions (including healthy) were conducted, majority of the studies were based on small cohorts (less than 100) and did not conduct independent/external validation on test sets.