Assessment of Contemporary Virtual Reality Programs and 3D Atlases in Neuroanatomical and Neurosurgical Education

Statement of Significance: The utilization of innovative technologies in medical education has received increasing attention in both undergraduate and graduate medical curricula. Understanding spatial, physiological, and pathological aspects of neuroanatomy are important for medical students and residents, alike. As virtual reality applications and platforms become more accessible to educators, learners, and the general public, such technology now represents a feasible modality of neuroanatomical education. This qualitative observational study compares and evaluates five programs based on the accessibility, breadth of content, and utility for various learner populations. Objective: Virtual reality (VR) is a growing technology of interest in medical education, particularly as the millennial generation has become the primary learners. We sought to compare the five available and affordable neuroanatomical programs with objective comparisons of the neuroanatomy, format, and target audience. Methods: The following programs were included: Sharecare VR, Organon VR, The Neurosurgical Atlas 3D Operative Neuroanatomy, BioDigital 3D Human Anatomy, 3D Brain. These programs were selected based on their price ($0-30) and platform (HTC Vive, Oculus Rift, iOS, Google Chrome). The following neuroanatomical categories were assessed: CNS, Cranial Nerves, PNS Skull, and Spine. Neuroanatomical level of detail was scored from 0 (absence of structure) to 3 (operative anatomy). Points were provided if programs included explanations of neuroanatomical relevance, models of pathology & physiology, references, and quiz features. These scores were tallied and compared. Results: The Neurosurgical Atlas and BioDigital scored highest (22 points each), followed by Organon VR (11), 3D Brain (9), and Sharecare VR (6). The Neurosurgical Atlas had the most detail with a score of 3 in each neuroanatomical category. BioDigital included more, but simpler, models. 3D Brain included simple CNS models, but useful explanations and references. Disappointingly, the VR-exclusive programs had entertainment-only models (Score = 1). Conclusions: The Neurosurgical Atlas is the most relevant and detailed model of neuroanatomy and is most appropriate for resident- or attending-level anatomic review. The remaining programs lacked detailed neuroanatomy limiting their potential for a neurosurgical audience.

Incorporating Semantic Similarity with Geographic Correlation for Query-POI Relevance Learning

Point-of-interest (POI) retrieval that searches for relevant destination locations plays a significant role in on-demand ridehailing services. Existing solutions to POI retrieval mainly retrieve and rank POIs based on their semantic similarity scores. Although intuitive, quantifying the relevance of a Query-POI pair by single-field semantic similarity is subject to inherent limitations. In this paper, we propose a novel Query-POI relevance model for effective POI retrieval for ondemand ride-hailing services. Different from existing relevance models, we capture and represent multi-field and local&global semantic features of a Query-POI pair to measure the semantic similarity. Besides, we observe a hidden correlation between origin-destination locations in ride-hailing scenarios, and propose two location embeddings to characterize the specific correlation. By incorporating the geographic correlation with the semantic similarity, our model achieves better performance in POI ranking. Experimental results on two real-world click-through datasets demonstrate the improvements of our model over state-of-the-art methods.

Learning relevance models for patient cohort retrieval

Objective We explored how judgements provided by physicians can be used to learn relevance models that enhance the quality of patient cohorts retrieved from Electronic Health Records (EHRs) collections. Methods A very large number of features were extracted from patient cohort descriptions as well as EHR collections. The features were used to investigate retrieving (1) neurology-specific patient cohorts from the de-identified Temple University Hospital electroencephalography (EEG) Corpus as well as (2) the more general cohorts evaluated in the TREC Medical Records Track (TRECMed) from the de-identified hospital records provided by the University of Pittsburgh Medical Center. The features informed a learning relevance model (LRM) that took advantage of relevance judgements provided by physicians. The LRM implements a pairwise learning-to-rank framework, which enables our learning patient cohort retrieval (L-PCR) system to learn from physicians’ feedback. Results and Discussion We evaluated the L-PCR system against state-of-the-art traditional patient cohort retrieval systems, and observed a 27% improvement when operating on EEGs and a 53% improvement when operating on TRECMed EHRs, showing the promise of the L-PCR system. We also performed extensive feature analyses to reveal the most effective strategies for representing cohort descriptions as queries, encoding EHRs, and measuring cohort relevance. Conclusion The L-PCR system has significant promise for reliably retrieving patient cohorts from EHRs in multiple settings when trained with relevance judgments. When provided with additional cohort descriptions, the L-PCR system will continue to learn, thus offering a potential solution to the performance barriers of current cohort retrieval systems.