Understanding cancer patient cohorts in virtual reality environment for better clinical decisions: a usability study

BACKGROUND

Visualising patient genomic data in a cohort with embedding data analytics models can provide relevant and sensible patient comparisons to assist a clinician with treatment decisions. As immersive technology is actively used around the medical world, there is a rising demand for an efficient environment that can effectively display genomic data visualisations on immersive devices such as a Virtual Reality (VR) environment. The VR technology will allow clinicians, biologists, and computer scientists to explore a cohort of individual patients within the 3D environment. However, demonstrating the feasibility of the VR prototype needs domain users' feedback for future user-centred design and a better cognitive model of human-computer interactions. There is limited research work for collecting and integrating domain knowledge into the prototype design.

OBJECTIVE

A usability study for the VR prototype--Virtual Reality to Observe Oncology data Models (VROOM) was implemented. VROOM was designed based on a preliminary study among medical users. The goals of this usability study included establishing a baseline of user experience, validating user performance measures, and identifying potential design improvements that are to be addressed to improve efficiency, functionality, and end-user satisfaction.

METHODS

The study was conducted with a group of domain users (10 males, 10 females) with portable VR devices and camera equipment. These domain users included medical users such as clinicians and genetic scientists and computing domain users such as bioinformatics and data analysts. Users were asked to complete routine tasks based on a clinical scenario. Sessions were recorded and analysed to identify potential areas for improvement to the data visual analytics projects in the VR environment. The one-hour usability study included learning VR interaction gestures, running visual analytics tool, and collecting before and after feedback. The feedback was analysed with different methods to measure effectiveness. The statistical method Mann-Whitney U test was used to analyse various task performances among the different participant groups, and multiple data visualisations were created to find insights from questionnaire answers.

RESULTS

The usability study investigated the feasibility of using VR for genomic data analysis in domain users' daily work. From the feedback, 65% of the participants, especially clinicians (75% of them), indicated that the VR prototype is potentially helpful for domain users' daily work but needed more flexibility, such as allowing them to define their features for machine learning part, adding new patient data, and importing their datasets in a better way. We calculated the engaged time for each task and compared them among different user groups. Computing domain users spent 50% more time exploring the algorithms and datasets than medical domain users. Additionally, the medical domain users engaged in the data visual analytics parts (approximately 20%) longer than the computing domain users.

Unsupervised machine learning models reveal predictive markers of glioblastoma patient survival using white blood cell counts prior to initiating chemoradiation

Purpose

Glioblastoma is a malignant brain tumor requiring careful clinical monitoring even after primary management. Personalized medicine has suggested use of various molecular biomarkers as predictors of patient prognosis or factors utilized for clinical decision making. However, the accessibility of such molecular testing poses a constraint for various institutes requiring identification of low-cost predictive biomarkers to ensure equitable care.

Methods

We collected retrospective data from patients seen at Ohio State University, University of Mississippi, Barretos Cancer Hospital (Brazil), and FLENI (Argentina) who were managed for glioblastoma-amounting to nearly 600 patient records documented using REDCap. Patients were evaluated using an unsupervised machine learning approach comprised of dimensionality reduction and eigenvector analysis to visualize the inter-relationship of collected clinical features.

Results

We discovered that white blood cell count of a patient during baseline planning for treatment was predictive of overall survival with an over 6-month median survival difference between the upper and lower quartiles of white blood cell count. By utilizing an objective PDL-1 immunohistochemistry quantification algorithm, we were further able to identify an increase in PDL-1 expression in glioblastoma patients with high white blood cell counts.

Conclusion

These findings suggest that in a subset of glioblastoma patients the incorporation of white blood cell count and PDL-1 expression in the brain tumor biopsy as simple biomarkers predicting glioblastoma patient survival. Moreover, use of machine learning models allows us to visualize complex clinical datasets to uncover novel clinical relationships.

Extractions in Patients with Periodontal Diseases and Clinical Decision-Making Process

Objectives

To investigate the professional aspects and clinical and radiographic evidence that influences the decision for the extraction of teeth among periodontologists and general dentists.

Material and methods

The sample consisted of 150 (n=106 females and 44 males) dentists (n=103 general dentists and 47 periodontologists) that responded to a questionnaire designed to retrieve cross-sectional information related mainly to their level of training and time of experience in practice, as well as their personal decision for managing four patients with periodontal disease. Bivariate analyses were performed to test the association between the clinical decisions and the professional information collected from the dentists.

Results

In specific cases, periodontologists decided to maintain more teeth than general dentists (p<0.05). In other cases, dentists with more years of experience in practice decided to opt for more extractions (p<0.05). The level of periodontal disease (50-92%), poor oral hygiene (42.6-67.3%) and lack of alveolar bone structure (43.2-79.3%) were the most prevalent reasons behind the decision for extractions.

Conclusions

An advanced level of training in Dentistry, especially Periodontology, and more years of experience in practice may lead to more well-founded decisions on whether extracting teeth or not in case-specific scenarios.

A Comparison of Physicians' and Nurse Practitioners' Use of Race in Clinical Decision-Making

Objective

The debate over use of race as a proxy for genetic risk of disease continues, but little is known about how primary care providers (nurse practitioners and general internal medicine physicians) currently use race in their clinical practice. Our study investigates primary care providers' use of race in clinical practice.

Methods

Survey data from three cross-sectional parent studies were used. A total of 178 nurse practitioners (NPs) and 759 general internal medicine physicians were included. The outcome of interest was the Racial Attributes in Clinical Evaluation (RACE) scale, which measures explicit use of race in clinical decision-making. Predictor variables included the Genetic Variation Knowledge Assessment Index (GKAI), which measures the providers' knowledge of human genetic variation.

Results

In the final multivariable model, NPs had an average RACE score that was 1.60 points higher than the physicians' score (P=.03). The GKAI score was not significantly associated with the RACE outcome in the final model (P=.67).

Conclusions

Physicians had more knowledge of genetic variation and used patients' race less in the clinical decision-making process than NPs. We speculate that these differences may be related to differences in discipline-specific clinical training and approaches to clinical care. Further exploration of these differences is needed, including examination of physicians' and NPs' beliefs about race, how they use race in disease screening and treatment, and if the use of race is contributing to health care disparities.

Clinical Pharmacogenomics: Applications in Nephrology

Pharmacogenomics is a tool for practitioners to provide precision pharmacotherapy using genomics. All providers are likely to encounter genomic data in practice with the expectation that they are able to successfully apply it to patient care. Pharmacogenomics tests for genetic variations in genes that are responsible for drug metabolism, transport, and targets of drug action. Variations can increase the risk for drug toxicity or poor efficacy. Pharmacogenomics can, therefore, be used to help select the best medication or aid in dosing. Nephrologists routinely treat cardiovascular disease and manage patients after kidney transplantation, two situations for which there are several high-evidence clinical recommendations for commonly used anticoagulants, antiplatelets, statins, and transplant medications. Successful use of pharmacogenomics in practice requires that providers are familiar with how to access and use pharmacogenomics resources. Similarly, clinical decision making related to whether to use existing data, whether to order testing, and if data should be used in practice is needed to deliver precision medicine. Pharmacogenomics is applicable to virtually every medical specialty, and nephrologists are well positioned to be implementation leaders.

Straight leg elevation to rule out pelvic injury

OBJECTIVE

Pelvic x-ray is frequently used as a screening tool during initial assessment of injured patients. However routine use in the awake and alert blunt trauma patient may be questioned due to low yield. We propose a clinical tool that may avoid unnecessary imaging by examining whether the ability to straight leg raise, without pain, can rule out pelvic injury.

METHODS

We conducted a prospective cohort study with the exposure variables of ability to straight leg raise and presence of pain on doing so, and presence of pelvic fracture on x-ray as the primary outcome variable.

RESULTS

Of the 328 participants, 35 had pelvic fractures, and of these 32 were either unable to straight leg raise, or had pain on doing so, with a sensitivity of 91.43% (95% CI: 76.94-98.2%) and a negative predictive value of 98.57% (95% CI: 95.88-99.70%). The 3 participants with a pelvic fracture who could straight leg raise with no pain, all had a GCS of less than 15, and therefore, among the sub-group of patients with GCS15, a 100% sensitivity and 100% negative predictive value for straight leg raise with no pain to rule out pelvic fracture was demonstrated.

CONCLUSION

Among awake, alert patients, painless straight leg raise can exclude pelvic fractures and be incorporated into initial examination during reception and resuscitation of injured patients.