Ryan Bahar

BACKGROUND: The molecular profile of gliomas is a prognostic indicator for survival, driving clinical decision-making for treatment. Pathology-based molecular diagnosis is challenging because of the invasiveness of the procedure, exclusion from neoadjuvant therapy options, and the heterogeneous nature of the tumor. PURPOSE: We performed a systematic review of algorithms that predict molecular subtypes of gliomas from MR Imaging. DATA SOURCES: Data sources were Ovid Embase, Ovid MEDLINE, Cochrane Central Register of Controlled Trials, Web of Science. STUDY SELECTION: Per the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 12,318 abstracts were screened and 1323 underwent full-text review, with 85 articles meeting the inclusion criteria. DATA ANALYSIS: We compared prediction results from different machine learning approaches for predicting molecular subtypes of gliomas. Bias analysis was conducted for each study, following the Prediction model Risk Of Bias Assessment Tool (PROBAST) guidelines. DATA SYNTHESIS: Isocitrate dehydrogenase mutation status was reported with an area under the curve and accuracy of 0.88 and 85% in internal validation and 0.86 and 87% in limited external validation data sets, respectively. For the prediction of O6-methylguanine-DNA methyltransferase promoter methylation, the area under the curve and accuracy in internal validation data sets were 0.79 and 77%, and in limited external validation, 0.89 and 83%, respectively. PROBAST scoring demonstrated high bias in all articles. LIMITATIONS: The low number of external validation and studies with incomplete data resulted in unequal data analysis. Comparing the best prediction pipelines of each study may introduce bias. CONCLUSIONS: While the high area under the curve and accuracy for the prediction of molecular subtypes of gliomas are reported in internal and external validation data sets, limited use of external validation and the increased risk of bias in all articles may present obstacles for clinical translation of these techniques.

In the past forty years, clinician-educators have become indispensable to academic medicine. Numerous clinician-educator-training programs exist within graduate medical education (GME) as clinician-educator tracks (CETs). However, there is a call for the clinician-educator pipeline to begin earlier. This work aims to identify and characterize clinician-educator track-like programs (CETLs) available in undergraduate medical education (UME). We developed an algorithm of 20 individual keyword queries to search the website of each U.S. allopathic medical school for CETLs. We performed the web search between March to April 2021 and repeated the search between July and September 2021. The search identified CETLs for 79 (51%) of the 155 U.S. allopathic medical schools. The identified CETLs commonly address the clinician-educator competency of educational theory (86%, 68/79), are formally organized as concentrations or analogous structures (52%, 41/79), and span all four years of medical school (37%, 29/79). The prevalence of CETLs varies with geography and medical school ranking. We provide an overview of the current state of CETLs as assessed from institutional websites. To create a future with a sustainable output of skilled clinician-educators, UME must continue to increase the number and quality of CETLs.

Background: While there are innumerable machine learning (ML) research algorithms used for segmentation of gliomas, there is yet to be a US FDA cleared product. The aim of this study is to explore the systemic limitations of research algorithms that have prevented translation from concept to product by a review of the current research literature. Methods: We performed a systematic literature review on 4 databases. Of 11 727 articles, 58 articles met the inclusion criteria and were used for data extraction and screening using TRIPOD. Results: We found that while many articles were published on ML-based glioma segmentation and report high accuracy results, there were substantial limitations in the methods and results portions of the papers that result in difficulty reproducing the methods and translation into clinical practice. Conclusions: In addition, we identified that more than a third of the articles used the same publicly available BRaTS and TCIA datasets and are responsible for the majority of patient data on which ML algorithms were trained, which leads to limited generalizability and potential for overfitting and bias.

Technological innovation has enabled the development of machine learning (ML) tools that aim to improve the practice of radiologists. In the last decade, ML applications to neuro-oncology have expanded significantly, with the pre-operative prediction of glioma grade using medical imaging as a specific area of interest. We introduce the subject of ML models for glioma grade prediction by remarking upon the models reported in the literature as well as by describing their characteristic developmental workflow and widely used classifier algorithms. The challenges facing these models—including data sources, external validation, and glioma grade classification methods —are highlighted. We also discuss the quality of how these models are reported, explore the present and future of reporting guidelines and risk of bias tools, and provide suggestions for the reporting of prospective works. Finally, this review offers insights into next steps that the field of ML glioma grade prediction can take to facilitate clinical implementation.

Objectives: To systematically review, assess the reporting quality of, and discuss improvement opportunities for studies describing machine learning (ML) models for glioma grade prediction.Methods: This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy (PRISMA-DTA) statement. A systematic search was performed in September 2020, and repeated in January 2021, on four databases: Embase, Medline, CENTRAL, and Web of Science Core Collection. Publications were screened in Covidence, and reporting quality was measured against the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) Statement. Descriptive statistics were calculated using GraphPad Prism 9.Results: The search identified 11,727 candidate articles with 1,135 articles undergoing full text review and 85 included in analysis. 67 (79%) articles were published between 2018-2021. The mean prediction accuracy of the best performing model in each study was 0.89 ± 0.09. The most common algorithm for conventional machine learning studies was Support Vector Machine (mean accuracy: 0.90 ± 0.07) and for deep learning studies was Convolutional Neural Network (mean accuracy: 0.91 ± 0.10). Only one study used both a large training dataset (n>200) and external validation (accuracy: 0.72) for their model. The mean adherence rate to TRIPOD was 44.5% ± 11.1%, with poor reporting adherence for model performance (0%), abstracts (0%), and titles (0%).Conclusions: The application of ML to glioma grade prediction has grown substantially, with ML model studies reporting high predictive accuracies but lacking essential metrics and characteristics for assessing model performance. Several domains, including generalizability and reproducibility, warrant further attention to enable translation into clinical practice.Systematic Review Registration: PROSPERO, identifier CRD42020209938.

Aims Long QT syndrome type 2 (LQT2) is caused by mutations in the gene KCNH2, encoding the hERG ion channel. Clinically, mild and severe phenotypes are associated with this cardiac channelopathy, complicating efforts to predict patient risk. The location of the mutation within KCNH2 contributes to this variable disease manifestation. Here we determined whether such phenotypic differences could be detected in cardiomyocytes derived from isogenic human induced pluripotent stem cells (hiPSCs) genetically edited to harbour a range of KCNH2 mutations. Methods and Results The hiPSC lines heterozygous for missense mutations either within the pore or tail region of the ion channel were generated using CRISPR-Cas9 editing and subsequently differentiated to cardiomyocytes (hiPSC-CMs) for functional assessment. Electrophysiological analysis confirmed the mutations prolonged the action potentials and field potentials of the hiPSC-CMs, with differences detected between the pore and tail region mutations when measured as paced 2D monolayers. This was also reflected in the cytosolic Ca²⁺ transients and contraction kinetics of the different lines. Pharmacological blocking of the hERG channel in the hiPSC-CMs also revealed that mutations in the pore-loop region conferred a greater susceptibility to arrhythmic events. Conclusion These findings establish that subtle phenotypic differences related to the location of the KCNH2 mutation in LQT2 patients are reflected in hiPSC-CMs under genetically controlled conditions. Moreover, the results validate hiPSC-CMs as a strong candidate for evaluating the underlying severity of individual KCNH2 mutations in humans which could ultimately facilitate patient risk stratification. Translational perspective Clinical management of patients diagnosed with cardiac channelopathy diseases such as LQT2 is complicated by the variable disease phenotypes observed among mutation carriers, creating challenges for diagnosis, risk stratification and treatment. The genotype of the patient contributes to this clinical heterogeneity, with the influence of the mutation’s location within KCNH2 on a patient’s risk of a cardiac event being an example. Here we demonstrate that under stringently controlled genetic and experimental conditions, hiPSC-CMs are able to reflect these subtle genotype-phenotype differences, thereby providing new opportunities to stratify and potentially lessen sudden cardiac death risk amongst KCNH2 mutation carriers.