Clinical Applications of Machine Learning.

Objective: This review introduces interpretable predictive machine learning approaches, natural language processing, image recognition, and reinforcement learning methodologies to familiarize end users. Background: As machine learning, artificial intelligence, and generative artificial intelligence become increasingly utilized in clinical medicine, it is imperative that end users understand the underlying methodologies. Methods: This review describes publicly available datasets that can be used with interpretable predictive approaches, natural language processing, image recognition, and reinforcement learning models, outlines result interpretation, and provides references for in-depth information about each analytical framework. Results: This review introduces interpretable predictive machine learning models, natural language processing, image recognition, and reinforcement learning methodologies. Conclusions: Interpretable predictive machine learning models, natural language processing, image recognition, and reinforcement learning are core machine learning methodologies that underlie many of the artificial intelligence methodologies that will drive the future of clinical medicine and surgery. End users must be well versed in the strengths and weaknesses of these tools as they are applied to patient care now and in the future.

For the Love of the Game: Calculating the Premium Associated with Academic Surgical Practice.

OBJECTIVE: We sought to determine the premium associated with a career in academic surgery, as measured by compensation normalized to the work relative value unit (wRVU). BACKGROUND: An academic surgical career, embodying innovation and mentorship, offers intrinsic rewards, but is not well monetized. We know compensation for academic surgeons is less than their non-academic counterparts, but the value of clinical effort, as normalized to the wRVU, between academic and non-academic surgeons has not been well characterized. Thus, we analyzed the variations in the valuation of academic and non-academic surgical work from 2010 to 2022. METHODS: We utilized Medical Group Management Association Provider Compensation data from 2010, 2014, 2018, and 2022 to compare academic and non-academic surgeons. We analyzed raw total cash compensation (TCC), wRVU, TCC per wRVU (TCC/wRVU), and TCC to collections (TCCtColl). We calculated collections per wRVU (Coll/wRVU). We adjusted TCC and TCCtColl for inflation using the Consumer Price Index. Linear modeling for trend analysis was performed. RESULTS: Compared to non-academic, academic surgeons had lower TCC (2010: $500,415.0±23,666 vs. $631,515.5±23,948.2, -21%; 2022: $564,789.8±23,993.9 vs. $628,247.4±15,753.2, -10%), despite higher wRVUs (2022: 9,109.4±474.9 vs. 8,062.7±252.7) and higher Coll/wRVU (2022: 76.68±8.15 vs. 71.80±6.10). Trend analysis indicated TCC will converge in 2038 at an estimated $660,931. CONCLUSIONS: In 2022, academic surgeons had more clinical activity and superior organizational revenue capture, despite less total and normalized clinical compensation. Based on TCC/wRVUs, academia charges a premium of 16% over non-academic surgery. However, trend analysis suggests that TCC will converge within the next twenty years.

Endovascular Salvage of Type Ia and Ib Endoleaks Using a Physician-Modified Fenestrated/Branched Endograft and an Iliac Branch Device Via Unilateral Transfemoral Arterial Access.

PURPOSE: This study aims to explore the feasibility and effectiveness of a unilateral transfemoral access endovascular salvage technique for complex abdominal aortic aneurysms with concurrent type Ia and Ib endoleaks following previous endovascular repair. CASE REPORT: A 69-year-old female with multiple comorbidities presented with an extent IV thoracoabdominal aortic aneurysm complicated by type Ia and Ib endoleaks and chronically occluded left iliac endoprosthesis after prior endovascular repair. Given the patient's medical complexities, open explant repair was deemed high risk. The case was successfully managed using a physician-modified fenestrated/branched endograft (PM-F/BEVAR) and an iliac branch device (IBD) deployed through a single percutaneous transfemoral access. CONCLUSION: The presented case demonstrates the safety and efficacy of PM-F/BEVAR with concomitant IBD deployment via unilateral transfemoral access. This innovative approach allows endovascular salvage in cases with restricted iliofemoral access and avoids the complexities associated with upper extremity or aortic arch manipulation. While acknowledging the technical challenges, this technique offers a viable alternative for salvaging failed endovascular repairs, emphasizing the importance of real-time modifications in achieving successful outcomes. Further studies and long-term follow-up are warranted to validate the broader applicability and durability of this approach in the management of complex abdominal aortic aneurysms with multiple endoleaks. CLINICAL IMPACT: Although not the conventional approach, unilateral transfemoral access can be utilized to implant either a physician-modified fenestrated aortic endograft or an iliac branch device. Such an approach avoids complicating issues related to upper extremity access. This innovative technique may be necessary when there is a failed prior EVAR in the setting of significant contralateral iliofemoral occlusive disease. Doing both procedures in the same setting to resolve a type Ia and Ib endoleak is feasible as demonstrated in this case report. Expanding the endovascular armamentarium to address EVAR failure will be increasingly useful in the future, especially given the morbidity profile of EVAR explantation.

The continued financial effect of COVID: Increasing costs for non-elective major lower extremity amputations.

Background: The COVID-19 pandemic necessitated changes in processes of care, which significantly impacted surgical care. This study evaluated the impact of these changes on patient outcomes and costs for non-elective major lower extremity amputations (LEA). Methods: The 2019-2021 Florida Agency for Health Care Administration database was queried for adult patients who underwent non-elective major LEA. Per-patient inflation-adjusted costs were collected. Patient cohorts were established based on Florida COVID-19 mortality rates: COVID-heavy (CH) included nine months with the highest mortality, COVID-light (CL) included nine months with the lowest mortality, and pre-COVID (PC) included nine months before COVID (2019). Outcomes included in-hospital patient outcomes and hospitalization cost. Results: 6132 patients were included (1957 PC, 2104 CH, and 2071 CL). Compared to PC, there was increased patient acuity at presentation, but morbidity (31%), mortality (4%), and length of stay (median 12 [8-17] days) were unchanged during CH and CL. Additionally, costs significantly increased during the pandemic; median total cost rose 9%, room costs increased by 16%, ICU costs rose by 15%, and operating room costs rose by 15%. When COVID-positive patients were excluded, cost of care was still significantly higher during CH and CL. Conclusions: Despite maintaining pre-pandemic standards, as evidenced by unchanged outcomes, the pandemic led to increased costs for patients undergoing non-elective major LEA. This was likely due to increased patient acuity, resource strain, and supply chain shortages during the pandemic. Key message: While patient outcomes for non-elective major lower extremity amputations remained consistent during the COVID-19 pandemic, healthcare costs significantly increased, likely due to increased patient acuity and heightened pressures on resources and supply chains. These findings underscore the need for informed policy changes to mitigate the financial impact on patients and healthcare systems for future public health emergencies.

Tension Pneumoperitoneum Following Attempted Pneumatic Reduction of Intussusception.

Tension pneumoperitoneum is a life-threatening complication of pneumatic reduction for intussusception if not immediately recognized and treated. We describe a 3-month-old woman who presented with intussusception, underwent attempted pneumatic reduction, and subsequently developed tension pneumoperitoneum with associated hemodynamic instability requiring emergent laparotomy. This is a known, rare complication of pneumatic reduction which highlights the need to have a high index of suspicion for early surgical management to obtain a positive outcome.

Traumatic Avulsion of Right Upper Lobe Bronchus in a Three-Year-Old.

Major bronchial injury during blunt trauma is a life-threatening occurrence in children. We describe a 3-year-old female who presented with a near circumferential tear at the takeoff of the right upper lobe bronchus after an all-terrain vehicle accident. This is an unusual blunt traumatic injury in the pediatric population and highlights the need for evaluation when a large, persistent air leak occurs after chest tube placement.

An Evaluation of Tension Measurements During Myofascial Release for Hernia Repair.

Tension-free repairs have revolutionized the way we repair hernias. To help reduce undue tension when performing ventral hernia repair, multiple different techniques of myofascial releases have been described. The purpose of this project is to evaluate tension measurements for commonly performed myofascial releases in abdominal wall hernia repair. Patients undergoing myofascial release techniques for their ventral hernias were enrolled in a prospective Institutional Review Board-approved protocol to measure abdominal wall tension from June 1, 2011 to August 1, 2019. Abdominal wall tensions were measured using tensiometers before and after myofascial release techniques. Descriptive statistics were performed and data were analyzed. Thirty patients had tension measurements (5 anterior myofascial separation, 25 posterior myofascial separation with transversus abdominis release [TAR]). Average age was 60.1 years (range 29-81), 83% Caucasian, 53% female, and 42% recurrent hernias. The average hernia defect in patients undergoing anterior myofascial release was 117.3 cm2, and the average mesh size was 650 cm2. The reduction in tension after anterior release was 4.7 lbs (2.7 lbs vs 7.4 lbs). The average hernia defect in patients undergoing posterior myofascial release (TAR) was 183 cm2, and the average mesh size was 761.36 cm2. The reduction in tension after bilateral posterior rectus sheath incision was 2.55 lbs (5.01 lbs vs 7.56 lbs) with 0.66 lbs further reduction in tension after TAR (4.35 lbs vs 5.01). In this evaluation, abdominal wall tension measurements are shown to be a feasible adjunct during open hernia repair. Preliminary data show tension reductions associated with the different myofascial release techniques and, with further study, may be a useful intraoperative adjunct for decision making in hernia repair.

Reliability and equivalence of alternate forms for the Symbol Digit Modalities Test: implications for multiple sclerosis clinical trials.

BACKGROUND: Cognitive impairment is common in multiple sclerosis (MS), but is seldom assessed in clinical trials investigating the effects of disease-modifying therapies. The Symbol Digit Modalities Test (SDMT) is a particularly promising tool due to its sensitivity and robust correlation with brain magnetic resonance imaging (MRI) and vocational disability. Unfortunately, there are no validated alternate SDMT forms, which are needed to mitigate practice effects. OBJECTIVE: The aim of the study was to assess the reliability and equivalence of SDMT alternate forms. METHODS: Twenty-five healthy participants completed each of five alternate versions of the SDMT - the standard form, two versions from the Rao Brief Repeatable Battery, and two forms specifically designed for this study. Order effects were controlled using a Latin-square research design. RESULTS: All five versions of the SDMT produced mean values within 3 raw score points of one another. Three forms were very consistent, and not different by conservative statistical tests. The SDMT test-retest reliability using these forms was good to excellent, with all r values exceeding 0.80. CONCLUSIONS: For the first time, we find good evidence that at least three alternate versions of the SDMT are of equivalent difficulty in healthy adults. The forms are reliable, and can be implemented in clinical trials emphasizing cognitive outcomes.