Artificial Intelligence and Black‐Box Medical Decisions: Accuracy versus Explainability

Although decision‐making algorithms are not new to medicine, the availability of vast stores of medical data, gains in computing power, and breakthroughs in machine learning are accelerating the pace of their development, expanding the range of questions they can address, and increasing their predictive power. In many cases, however, the most powerful machine learning techniques purchase diagnostic or predictive accuracy at the expense of our ability to access “the knowledge within the machine.” Without an explanation in terms of reasons or a rationale for particular decisions in individual cases, some commentators regard ceding medical decision‐making to black box systems as contravening the profound moral responsibilities of clinicians. I argue, however, that opaque decisions are more common in medicine than critics realize. Moreover, as Aristotle noted over two millennia ago, when our knowledge of causal systems is incomplete and precarious—as it often is in medicine—the ability to explain how results are produced can be less important than the ability to produce such results and empirically verify their accuracy.     

The impact of canister geometry on chemical biological radiological and nuclear filter performance: A computational fluid dynamics analysis

Steady-state axisymmetric simulations using the Reynolds-Averaged Navier-Stokes equations have been carried out in order to optimize the performance of a Chemical, Biological, Radiological, and Nuclear (CBRN) canister filter for its use in a powered air-purifying respirator (PAPR). Alterations have been made to the shape of the canister, the spacing of the rear wall of the canister with regard to the carbon filter, and the bracketing between (i) the particulate filter and the carbon bed and (ii) the carbon bed and the canister wall. The pressure drops across the canister and the residence time distribution at the rear of the carbon bed have been analyzed in detail based on an extensive parametric analysis involving the aforementioned variations. It has been demonstrated that the non-uniform porosity profile of the carbon bed resulted in alternating regions of high and low velocity close to the canister wall, providing a possible route for breakthrough. Designs, which included a bracket at the rear of the carbon bed, blocked this route and consequently had a longer minimum mean residence time than those, which did not. It has also been shown that the spacing between the carbon bed and the canister rear wall had a large impact on both residence time and pressure drop. In cases where the carbon backed directly onto the canister rear wall flow in the axial direction from the outside wall toward the canister axis resulted in far greater pressure drop and a reduction in minimum mean residence time within the carbon bed.     

Clinical presentation of young people (10–24 years old) with brain tumors: results from the international MOBI-Kids study

Journal of Neuro-Oncology - We used data from MOBI-Kids, a 14-country international collaborative case–control study of brain tumors (BTs), to study clinical characteristics of the tumors in...     

Patterns of relapse after successful completion of initial therapy in primary central nervous system lymphoma: a case series

Journal of Neuro-Oncology - Primary central nervous system lymphoma (PCNSL) is a subtype of non-Hodgkin’s lymphoma that involves the brain, spinal cord, or leptomeninges, without evidence of...     

Effects of exercise dose and type during breast cancer chemotherapy on longer-term patient-reported outcomes and health-related fitness: A randomized controlled trial

The Combined Aerobic and Resistance Exercise (CARE) Trial compared different types and doses of exercise performed during breast cancer chemotherapy. Here, we report the longer-term follow-up of patient-reported outcomes, health-related fitness and exercise behavior at 6, 12 and 24 months postintervention. A multicenter trial in Canada randomized 301 breast cancer patients initiating chemotherapy to thrice weekly, supervised exercise consisting of a standard dose of 25–30 min of aerobic exercise (STAN; n = 96), a higher dose of 50–60 min of aerobic exercise (HIGH; n = 101) or a combined dose of 50–60 min of aerobic and resistance exercise (COMB; n = 104) performed for the duration of chemotherapy (median of 17 weeks). Primary outcomes were patient-reported outcomes including quality of life, cancer-related symptoms and psychosocial outcomes. Secondary outcomes were objective health-related fitness (assessed at 12 months only) and self-reported exercise behavior. A total of 269 (89.4%) participants completed patient-reported outcomes at all three follow-up time points and 263 (87.4%) completed the health-related fitness assessment at 12-month follow-up. COMB was significantly superior to (i) STAN for sleep quality at 6-month follow-up (p = 0.027); (ii) HIGH for upper body muscular endurance at 12-month follow-up (p = 0.020); and (iii) HIGH for meeting the resistance exercise guideline at 6-month follow-up (p = 0.006). Moreover, self-reported meeting of the combined exercise guideline during follow-up was significantly associated with better patient-reported outcomes and health-related fitness. Performing combined exercise during and after breast cancer chemotherapy may result in better longer-term patient-reported outcomes and health-related fitness compared to performing aerobic exercise alone.     

Utilization of hypofractionated radiation therapy in older glioblastoma patients

Background

Though the optimal treatment regimen in older patients with glioblastoma multiforme (GBM) remains to be established, multiple randomized studies have supported the use of hypofractionated (1–3?weeks) versus traditional regimens (6?weeks). Here we examine hypofractionated regimen practice patterns among older patients with GBM.

Confidentiality Discussions and Private Time With a Health-Care Provider for Youth,United States, 2016

Purpose

The objective of the study was to define factors associated with adolescent and young adult (AYA) experiences with private time and having discussed confidentiality and the impact of these experiences on improving delivery of clinical preventive services.