Evaluation of the impact of artificial intelligence-assisted image interpretation on the diagnostic performance of clinicians in identifying pneumothoraces on plain chest X-ray: a multi-case multi-reader study.

BACKGROUND: Artificial intelligence (AI)-assisted image interpretation is a fast-developing area of clinical innovation. Most research to date has focused on the performance of AI-assisted algorithms in comparison with that of radiologists rather than evaluating the algorithms' impact on the clinicians who often undertake initial image interpretation in routine clinical practice. This study assessed the impact of AI-assisted image interpretation on the diagnostic performance of frontline acute care clinicians for the detection of pneumothoraces (PTX). METHODS: A multicentre blinded multi-case multi-reader study was conducted between October 2021 and January 2022. The online study recruited 18 clinician readers from six different clinical specialties, with differing levels of seniority, across four English hospitals. The study included 395 plain CXR images, 189 positive for PTX and 206 negative. The reference standard was the consensus opinion of two thoracic radiologists with a third acting as arbitrator. General Electric Healthcare Critical Care Suite (GEHC CCS) PTX algorithm was applied to the final dataset. Readers individually interpreted the dataset without AI assistance, recording the presence or absence of a PTX and a confidence rating. Following a 'washout' period, this process was repeated including the AI output. RESULTS: Analysis of the performance of the algorithm for detecting or ruling out a PTX revealed an overall AUROC of 0.939. Overall reader sensitivity increased by 11.4% (95% CI 4.8, 18.0, p=0.002) from 66.8% (95% CI 57.3, 76.2) unaided to 78.1% aided (95% CI 72.2, 84.0, p=0.002), specificity 93.9% (95% CI 90.9, 97.0) without AI to 95.8% (95% CI 93.7, 97.9, p=0.247). The junior reader subgroup showed the largest improvement at 21.7% (95% CI 10.9, 32.6), increasing from 56.0% (95% CI 37.7, 74.3) to 77.7% (95% CI 65.8, 89.7, p<0.01). CONCLUSION: The study indicates that AI-assisted image interpretation significantly enhances the diagnostic accuracy of clinicians in detecting PTX, particularly benefiting less experienced practitioners. While overall interpretation time remained unchanged, the use of AI improved diagnostic confidence and sensitivity, especially among junior clinicians. These findings underscore the potential of AI to support less skilled clinicians in acute care settings.

Benefits of Resistance Training During Pregnancy for Maternal and Fetal Health: A Brief Overview.

Research demonstrates resistance training is not only safe but also beneficial for pregnant women. However, exercise recommendations for pregnant women still minimize the importance of resistance exercise and provide minimal guidance. With a large increase in strength-focused sports among women, it is critical to re-evaluate the risk/benefit ratio of these exercises and ensure the latest recommendations reflect the latest clinical research. The purpose of this review is to highlight the safety and benefits of resistance training for both maternal and fetal health, particularly focusing on recent work. Relevant research involving resistance training during pregnancy was accessed and analyzed via a quasi-systematic search. Results demonstrate that appropriate prenatal resistance training can help alleviate some of the common symptoms of pregnancy, such as fatigue, back pain, and poor mental health. Resistance exercise can assist with glucose control in gestational diabetes mellitus, as well as decrease the risk of infant macrosomia and childhood metabolic dysfunction associated with uncontrolled gestational diabetes. Resistance training can also increase the likelihood of a vaginal delivery, which is beneficial for both mother and baby. Concerning fetal health, resistance training increases uterine blood flow, decreases the risk of neonatal macrosomia, and improves cognitive function and metabolic health in childhood. As with all forms of exercise, pregnant women should avoid resistance exercises that involve the supine position for extended bouts of time, trauma (or risk of trauma) to the abdomen, ballistic movements, movements that rely heavily on balance, and conditions that prohibit appropriate temperature control. With these considerations in mind, resistance training's benefits far surpass the lack of risk to the fetus. Resistance training is a safe and effective way to improve and maintain physical fitness during pregnancy and represents no risk to fetal health and development. Thus, healthcare providers should recommend resistance training for pregnant women.

Feasibility and Clinical Utility of Reporting Hereditary Cancer Predisposition Pathogenic Variants Identified in Research Germline Sequencing: A Prospective Interventional Study.

PURPOSE: Patients with cancer frequently undergo research-grade germline sequencing but clinically actionable results are not routinely disclosed. The objective of this study is to evaluate the feasibility of reporting clinically relevant secondary findings (SF) identified in germline research sequencing using the institutional molecular tumor board (MTB) and the treating oncology physician. METHODS: This prospective, interventional cohort study enrolled Total Cancer Care participants with any cancer diagnosis at a single institution. Patients underwent research-grade germline whole-exome sequencing, with bioinformatic analysis in a Clinical Laboratory Improvement Amendments-certified laboratory to verify pathogenic/likely pathogenic germline variants (PGVs) in any American College of Medical Genomics and Genetics SF v2.0 genes. After a protocol modification in consenting patients, the MTB reported PGVs to treating oncology physicians with recommendations for referral to a licensed genetic counselor and clinical confirmatory testing. RESULTS: Of the 781 enrolled participants, 32 (4.1%) harbored cancer predisposition PGVs, 24 (3.1%) were heterozygous carriers of an autosomal recessive cancer predisposition syndrome, and 14 (1.8%) had other hereditary disease PGVs. Guideline-directed testing would have missed 37.5% (12/32) of the inherited cancer predisposition PGVs, which included BRCA1, BRCA2, MSH6, SDHAF2, SDHB, and TP53 variants. Three hundred fifteen participants consented to reporting results; results for all living patients were reported to the clinical team with half referred to a licensed genetic counselor. There was concordance between all research variants identified in patients (n = 9) who underwent clinical confirmatory sequencing. CONCLUSION: MTB reporting of research-grade germline sequencing to the clinical oncology team is feasible. Over a third of PGVs identified using a universal testing strategy would have been missed by guideline-based approach, suggesting a role for expanding germline testing.

Video-Assisted Thoracoscopic or Open Lobectomy in Early-Stage Lung Cancer.

BACKGROUND: There is limited randomized evidence on the comparative outcomes of early-stage lung cancer resection by video-assisted thoracoscopic surgery (VATS) versus open resection. METHODS: We conducted a parallel-group multicenter randomized trial that recruited participants with known or suspected early-stage lung cancer and randomly assigned them to open or VATS resection of their lesions. The primary outcome was physical function at 5 weeks as a measure of recovery using the European Organisation for Research and Treatment of Cancer core health-related quality of life questionnaire (QLQ-C30) (scores range from 0 to 100, with higher scores indicating better function; the clinical minimally important difference for improvement is 5 points). We followed the patients for an additional 47 weeks for other outcomes. RESULTS: A total of 503 participants were randomly assigned (247 to VATS and 256 to open lobectomy). At 5 weeks, median physical function was 73 in the VATS group and 67 in the open surgery group, with a mean difference of 4.65 points (95% confidence interval, 1.69 to 7.61). Of the participants allocated to VATS, 30.7% had serious adverse events after discharge compared with 37.8% of those allocated to open surgery (risk ratio, 0.81 [95% confidence interval, 0.66 to 1.00]). At 52 weeks, there were no differences in cancer progression-free survival (hazard ratio, 0.74 [0.43 to 1.27]) or overall survival (hazard ratio, 0.67 [0.32 to 1.40]). CONCLUSIONS: VATS lobectomy for lung cancer is associated with a better recovery of physical function in the 5 weeks after random assignment compared with open surgery. Long-term oncologic outcomes will require continued follow-up to assess. (Funded by the National Institute for Health Research Health Technology Assessment programme [reference number 13/04/03]; ISRCTN number, ISRCTN13472721.)