Simulating Dual-Energy X-Ray Absorptiometry in CT Using Deep-Learning Segmentation Cascade

PurposeOsteoporosis is an underdiagnosed condition despite effective screening modalities. Dual-energy x-ray absorptiometry (DEXA) screening, although recommended in clinical guidelines, remains markedly underutilized. In contrast to DEXA, CT utilization is high and presents a valuable data source for opportunistic osteoporosis screening. The purpose of this study was to describe a method to simulate lumbar DEXA scores from routinely acquired CT studies using a machine-learning algorithm.MethodsBetween January 2010 and September 2014, 610 CT studies of the abdomen and pelvis were used to develop spinal column and L1 to L4 multiclass segmentation. DEXA simulation training and validation used 1,843 pairs of CT studies accompanied by DEXA results obtained within a 6-month interval from the same individual. Machine learning–based regression was used to determine correlation between calculated grade (on the basis of vertebrae L1-L4) and DEXA t score.ResultsAnalysis of the t score equivalent, generated by the algorithm, revealed true positives in 1,144 patients, false positives in 92 patients, true negatives in 245 patients, and false negatives in 212 patients, resulting in an accuracy of 82%. Sensitivity for the detection of osteoporosis or osteopenia was 84.4% (95% confidence interval, 82.3%-86.2%), and specificity was 72.7% (95% confidence interval, 67.7%-77.2%).ConclusionsThe presented algorithm can identify osteoporosis and osteopenia with a high degree of accuracy (82%) and a small proportion of false positives. Efforts to cull greater information using machine-learning algorithms from pre-existing data have the potential to have a marked impact on population health efforts such as bone mineral density screening for osteoporosis, in which gaps in screening currently exist.     

Adolescents and Drug Abuse: 21st Century Synthetic Substances

Illicit drug use by adolescents is an old problem with new clinical challenges, as teens access synthetic drugs in schools, on the street, and through internet purchase. Detection of synthetic drugs and unknown adulterants is often impossible using standard drug screens, but may be identified with the assistance of regional poison centers and the forensic laboratories of local universities and law enforcement, including the Drug Enforcement Agency. While clinical care for most intoxication and overdose cases is still largely supportive, critical interventions may be necessary for some. Toxicology experts at poison centers not only provide management advice contemporaneous to care, but compile data to identify local dangerous drug activity. This article reviews current knowledge of synthetic cannabinoids, amphetamines, and opioids, as well as the increasing teen use of “vaping” devices for delivery of tobacco and other substances.     

Are Incoming Pediatric Interns Ready to Obtain the Essential Components of an Informed Consent for Lumbar Puncture?

ObjectiveIn 2013, the Association of American Medical Colleges created the “Core Entrustable Professional Activities (EPAs) for Entering Residency” to more clearly define the set of activities that entering residents should be able to perform on day 1 of residency without direct supervision. EPA #11 is obtaining informed consent for tests and/or procedures. This EPA acknowledges that an entrustable learner should be able to document a complete consent among other components. The aim of this study is to explore whether incoming pediatric interns demonstrated the behaviors of an “entrustable learner” in the domain of documenting informed consent for a common pediatric procedure.MethodsAll incoming interns in our program (2007–2017) completed a 6-station Objective Structured Clinical Examination during residency orientation. One of the scenarios involves obtaining parental consent for a lumbar puncture (LP). The researchers determined and agreed what components would be important for a complete and accurately documented consent. A retrospective review of the resident's written informed consents occurred looking for accuracy of documented components.ResultsOf the 258 consents reviewed, 8 were complete and accurate. Incoming interns appear to be skilled when completing the basics of the informed consent form such as documenting names, obtaining signatures, and correctly identifying the procedure. However, detailing all the risks of the LP were areas for which they did not demonstrate proficiency.ConclusionsDocumenting informed consent is not adequately demonstrated by our learners prior to the beginning of internship. We would recommend specific training before entrusting pediatric interns to obtain LP consent independently.