Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency.

Importance: The efficient and accurate interpretation of radiologic images is paramount. Objective: To evaluate whether a deep learning-based artificial intelligence (AI) engine used concurrently can improve reader performance and efficiency in interpreting chest radiograph abnormalities. Design, Setting, and Participants: This multicenter cohort study was conducted from April to November 2021 and involved radiologists, including attending radiologists, thoracic radiology fellows, and residents, who independently participated in 2 observer performance test sessions. The sessions included a reading session with AI and a session without AI, in a randomized crossover manner with a 4-week washout period in between. The AI produced a heat map and the image-level probability of the presence of the referrable lesion. The data used were collected at 2 quaternary academic hospitals in Boston, Massachusetts: Beth Israel Deaconess Medical Center (The Medical Information Mart for Intensive Care Chest X-Ray [MIMIC-CXR]) and Massachusetts General Hospital (MGH). Main Outcomes and Measures: The ground truths for the labels were created via consensual reading by 2 thoracic radiologists. Each reader documented their findings in a customized report template, in which the 4 target chest radiograph findings and the reader confidence of the presence of each finding was recorded. The time taken for reporting each chest radiograph was also recorded. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were calculated for each target finding. Results: A total of 6 radiologists (2 attending radiologists, 2 thoracic radiology fellows, and 2 residents) participated in the study. The study involved a total of 497 frontal chest radiographs-247 from the MIMIC-CXR data set (demographic data for patients were not available) and 250 chest radiographs from MGH (mean [SD] age, 63 [16] years; 133 men [53.2%])-from adult patients with and without 4 target findings (pneumonia, nodule, pneumothorax, and pleural effusion). The target findings were found in 351 of 497 chest radiographs. The AI was associated with higher sensitivity for all findings compared with the readers (nodule, 0.816 [95% CI, 0.732-0.882] vs 0.567 [95% CI, 0.524-0.611]; pneumonia, 0.887 [95% CI, 0.834-0.928] vs 0.673 [95% CI, 0.632-0.714]; pleural effusion, 0.872 [95% CI, 0.808-0.921] vs 0.889 [95% CI, 0.862-0.917]; pneumothorax, 0.988 [95% CI, 0.932-1.000] vs 0.792 [95% CI, 0.756-0.827]). AI-aided interpretation was associated with significantly improved reader sensitivities for all target findings, without negative impacts on the specificity. Overall, the AUROCs of readers improved for all 4 target findings, with significant improvements in detection of pneumothorax and nodule. The reporting time with AI was 10% lower than without AI (40.8 vs 36.9 seconds; difference, 3.9 seconds; 95% CI, 2.9-5.2 seconds; P < .001). Conclusions and Relevance: These findings suggest that AI-aided interpretation was associated with improved reader performance and efficiency for identifying major thoracic findings on a chest radiograph.

Impact of Preoperative Acetaminophen and Carbohydrate Loading on Pain and Functional Status in Patients Undergoing Mohs Micrographic Surgery for Nonmelanoma Skin Cancers.

BACKGROUND: Preoperative acetaminophen and carbohydrate loading has been shown to improve the functional recovery of surgical patients. OBJECTIVE: To determine the effects of preoperative acetaminophen and carbohydrates on functional outcomes and the use of pain medications after surgery in patients undergoing Mohs Micrographic Surgery (MMS) for nonmelanoma skin cancer (NMSC). MATERIALS AND METHODS: One hundred patients treated with MMS for NMSC at an academic center were randomized into a control group receiving standard preoperative care or an intervention group receiving acetaminophen and carbohydrate drinks immediately before surgery. Patients rated levels of pain, thirst, hunger, anxiety, and fatigue on the day of surgery on a scale of 0 to 100, and reported through a phone interview the use of pain medications within 48 hours of surgery. RESULTS: There was no significant difference between intervention and control groups in maximum pain score on the day of surgery; maximum pain score 48 hours after surgery; use of nonopioid pain medications; and use of opioids. However, the intervention group had lower anxiety levels during and at the end of surgery. CONCLUSION: Patients undergoing MMS for NMSC reported very low levels of pain during and after surgery. Preoperative acetaminophen and carbohydrate loading had no impact on pain levels or the use of pain medications but did reduce levels of anxiety.

The 22-Modifier in Reimbursement for Orthopedic Procedures: Hip Arthroplasty and Obesity Are Worth the Effort.

BACKGROUND: Orthopedic surgeons utilize the 22-modifier when billing for complex procedures under the American Medical Association's Current Procedural Terminology (CPT) for reasons such as excessive blood loss, anatomic abnormality, and morbid obesity, cases that would ideally be reimbursed at a higher rate to compensate for additional physician work and time. We investigated how the 22-modifier affects physician reimbursement in knee and hip arthroplasty. METHODS: We queried hospital billing data from 2009 to 2016, identifying all cases performed at our urban tertiary care orthopedic center for knee arthroplasty (CPT codes 27438, 27447, 27487, and 27488) and hip arthroplasty (CPT codes 27130, 27132, 27134, 27236). We extracted patient insurance status and reimbursement data to compare the average reimbursement between cases with and without the 22-modifier. RESULTS: We analyzed data from 2605 procedures performed by 10 providers. There were 136 cases with 22-modifiers. For knee arthroplasty (n = 1323), the 22-modifier did not significantly increase reimbursement after adjusting for insurer, provider, and fiscal year (4.2% dollars higher on average, P = .159). For hip arthroplasty (n = 1282), cases with a 22-modifier had significantly higher reimbursement than those without the 22-modifier (6.2% dollars more, P = .049). For hip arthroplasty cases with a 22-modifier, those noting morbid obesity were reimbursed 29% higher than those cases with other etiology. CONCLUSIONS: The effect of the 22-modifier on reimbursement amount is differential between knee and hip arthroplasty. Hip arthroplasty procedures coded as 22-modifier are reimbursed more than those without the 22-modifier. Providers should consider these potential returns when considering submitting a 22-modifier.