Journal of Surgical Research最新文献

{"title":"Preoperative Biopsy Is Not Associated With Adverse Outcomes in Patients With Pancreatic Ductal Adenocarcinoma Undergoing Upfront Resection","authors":"Maximiliano Servin-Rojas MD ,&nbsp;Louisa Bolm MD ,&nbsp;Keith D. Lillemoe MD,&nbsp;Zhi Ven Fong MD, MPH, DrPH,&nbsp;Raja R. Narayan MD, MPH,&nbsp;Carlos Fernández-Del Castillo MD,&nbsp;Motaz Qadan MD, PhD","doi":"10.1016/j.jss.2025.01.007","DOIUrl":"10.1016/j.jss.2025.01.007","url":null,"abstract":"<div><h3>Introduction</h3><div>Obtaining a preoperative histological diagnosis in patients with resectable pancreatic disease has traditionally not been routinely sought, citing concerns in biopsy-associated complications, and risk of tumor seeding. We sought to determine if preoperative biopsy was associated with worse outcomes, including overall survival (OS).</div></div><div><h3>Methods</h3><div>This was a retrospective analysis of the National Cancer Database including adult patients with clinical stage I-III pancreatic ductal adenocarcinoma who underwent upfront surgical resection. Univariate and multivariable analyses were conducted to determine if undergoing a preoperative biopsy was associated with impaired OS, increased 30-d readmissions, or delayed return to intended oncologic therapy (RIOT), defined by receipt of adjuvant therapy.</div></div><div><h3>Results</h3><div>A total of 19,361 patients underwent upfront resection, of whom 11,038 (57%) underwent preoperative biopsy. Patients were more likely to undergo a preoperative biopsy if they were Black (11% <em>versus</em> 9%, <em>P</em> = 0.003), privately insured (34% <em>versus</em> 32%, <em>P</em> &lt; 0.001), treated at academic facilities (58% <em>versus</em> 56%, <em>P</em> &lt; 0.001), had tail tumors (14% <em>versus</em> 13%, <em>P</em> = 0.006), and were clinical stage II (44% <em>versus</em> 40%, <em>P</em> &lt; 0.001). There was no difference in median OS between groups (23.0 mos <em>versus</em> 23.5 mos, <em>P</em> = 0.21). In multivariable analysis, preoperative biopsy did not predict OS, 30-d readmissions, or RIOT.</div></div><div><h3>Conclusions</h3><div>Preoperative biopsy was conducted in 57% of patients undergoing upfront resection and was not associated with impaired OS. Although surgical complications could not be evaluated, there were no differences in 30-d readmissions or RIOT. Preoperative biopsy appears oncologically safe and may help ensure an accurate diagnosis before pancreatectomy.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"307 ","pages":"Pages 33-41"},"PeriodicalIF":1.8,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simplified Enhanced Recovery After Surgery Intraoperative Fluid Management","authors":"Hilary Gallin MD, MBA ,&nbsp;Marcus V. Ortega MD ,&nbsp;Rachel Sisodia MD ,&nbsp;Jason H. Wasfy MD MPhil ,&nbsp;Jeffrey Ecker MD ,&nbsp;Michael Dezube MEng ,&nbsp;Michael K. Hidrue PhD ,&nbsp;Marcela G. del Carmen MD, MPH ,&nbsp;Dan B. Ellis MD","doi":"10.1016/j.jss.2025.01.006","DOIUrl":"10.1016/j.jss.2025.01.006","url":null,"abstract":"<div><h3>Introduction</h3><div>This study evaluates the efficacy of a simplified intraoperative fluid administration metric within enhanced recovery after surgery (ERAS) pathways. The objective is to optimize fluid management to improve postoperative outcomes, specifically kidney function.</div></div><div><h3>Methods</h3><div>A retrospective evaluation was conducted at Massachusetts General Hospital on adult patients who underwent open hysterectomy, colectomy, and gastrectomy as part of ERAS pathways. The proposed fluid metric, set at 500 mL/h, was assessed against traditional methods of fluid administration. Data on serum creatinine (Cr) changes as defined as the difference between the baseline value and the maximum value within 1 week of surgery were collected, and compliance with the metric was monitored. Analysis involved Wilcoxon rank-sum test, Kruskal–Wallis test, and quantile regression.</div></div><div><h3>Results</h3><div>The study included 1028 patients. Regression analysis indicated that compared to patients who received the optimal fluid quantity, those receiving below the optimal range showed an absolute increase in median Cr levels of 0.03 mg/dl (95% confidence interval = −0.005, 0.05) while those who received above the optimal range demonstrated an absolute increase in median Cr level of 0.01 (95% confidence interval = −0.03, 0.05).</div></div><div><h3>Conclusions</h3><div>The new fluid metric demonstrated a balanced approach to fluid administration, reducing the risk of overhydration while maintaining sufficient hydration. Additionally, implementing a simplified fluid metric of 500 mL/h in ERAS pathways is effective in improving postoperative kidney function. This approach facilitates adherence to fluid guidelines and can be applied across various healthcare settings. This metric serves as a practical, evidence-based pathway for fluid administration for most patients undergoing most ERAS procedures.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"307 ","pages":"Pages 14-20"},"PeriodicalIF":1.8,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risk of Severe Sepsis After Blood Product Administration for Traumatic Hemorrhage: A Trauma Quality Improvement Program Study","authors":"Lauren T. Gallagher MD ,&nbsp;Mitchell J. Cohen MD ,&nbsp;Franklin L. Wright MD ,&nbsp;Julie M. Winkle MD ,&nbsp;David J. Douin MD ,&nbsp;Michael D. April MD, DPhil, MSc ,&nbsp;Andrew D. Fisher MD, MPAS ,&nbsp;Julie A. Rizzo MD ,&nbsp;Steven G. Schauer DO, MS","doi":"10.1016/j.jss.2024.12.009","DOIUrl":"10.1016/j.jss.2024.12.009","url":null,"abstract":"<div><h3>Introduction</h3><div>Transfusion of whole blood (WB) for traumatic hemorrhage has generated renewed interest in civilian trauma based on military experience. The association between blood products and severe sepsis remains unknown. We sought to determine which blood products were associated with the development of severe sepsis.</div></div><div><h3>Methods</h3><div>We utilized the TQIP database from 2020 to 2021. We included patients ≥15 ys of age who received at least one blood product and survived at least 24 hs. Severe sepsis is a standardized core quality measure for all reporting centers and defined as sepsis with organ dysfunction. We used descriptive, inferential, and multivariable logistic regression methods to test for associations and adjust for confounders.</div></div><div><h3>Results</h3><div>There were 83,924 patients included, of whom 1471 met criteria for severe sepsis. Patients with severe sepsis tended to be older (47 <em>versus</em> 42, <em>P</em> &lt; 0.001), male (79% <em>versus</em> 74%, <em>P</em> &lt; 0.001), have a higher injury severity score (29 <em>versus</em> 19, <em>P</em> &lt; 0.001), higher proportion of serious injuries to the thorax (65% <em>versus</em> 47%, <em>P</em> &lt; 0.001), abdomen (54% <em>versus</em> 32%, <em>P</em> &lt; 0.001), and extremities (45% <em>versus</em> 32%, <em>P</em> &lt; 0.001). Severe sepsis patients received more packed red cells, WB, platelets, cryoprecipitate, and plasma. When adjusting for age, sex, mechanism of injury, and injury severity score, WB was positively associated with severe sepsis (unit odds ratio 1.04, 95% confidence interval 1.01-1.07).</div></div><div><h3>Conclusions</h3><div>Within this dataset, we found a 4% increased odds of sepsis with each unit of WB received among civilian trauma patients. The effects of blood product administration on immune system function remain unclear. High-quality, prospective explanatory studies are needed to better understand this relationship.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"307 ","pages":"Pages 8-13"},"PeriodicalIF":1.8,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative Artificial Intelligence in Academic Surgery: Ethical Implications and Transformative Potential.","authors":"Jamie R Robinson, Anne Stey, David F Schneider, Anai N Kothari, Brenessa Lindeman, Haytham M Kaafarani, Krista L Haines","doi":"10.1016/j.jss.2024.12.059","DOIUrl":"https://doi.org/10.1016/j.jss.2024.12.059","url":null,"abstract":"<p><p>Artificial intelligence (AI) is rapidly being used in medicine due to its advanced capabilities in image and video recognition, clinical decision support, surgical education, and administrative task automation. Large language models such as OpenAI's Generative Pretrained Transformer (GPT)-4 and Google's Bard have particularly revolutionized text generation, offering substantial benefits for the academic surgeon, including aiding in manuscript and grant writing. However, integrating AI into academic surgery necessitates addressing ethical concerns such as bias, transparency, and intellectual property. This paper provides guidelines and recommendations based on current literature around the opportunities and ethical challenges of AI in academic surgery. We discuss the underlying mechanisms of large language models, their potential biases, and the importance of responsible usage. Furthermore, we explore the ethical implications of AI in clinical documentation, highlighting improved efficiency and necessary privacy concerns. This review also addresses the critical issue of intellectual property dilemmas posed by AI-generated innovations in university settings. Finally, we propose guidelines for the responsible adoption of AI in academic and clinical environments, stressing the need for transparency, ethical training, and robust governance frameworks to ensure AI enhances, rather than undermines, academic integrity and patient care.</p>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143399379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient Free Flap Monitoring—A Single-Center Study Comparing Different Monitoring Periods","authors":"David Kampshoff MD ,&nbsp;Charalampos Varnava MD ,&nbsp;Alexander Dermietzel MD ,&nbsp;Philipp Wiebringhaus MD ,&nbsp;Tobias Hirsch MD ,&nbsp;Maximilian Kueckelhaus MD, MBA","doi":"10.1016/j.jss.2024.12.056","DOIUrl":"10.1016/j.jss.2024.12.056","url":null,"abstract":"<div><h3>Introduction</h3><div>Postoperative monitoring is an important part in the complex process of reconstructive microsurgery. While it can improve quality and outcome of microsurgical reconstructions, it is also very resource intensive. The aim of this study was to investigate the effectiveness of postoperative flap monitoring.</div></div><div><h3>Methods</h3><div>In this study, we analyzed outcomes and complications after microsurgical reconstruction. The initial postoperative monitoring period was operation day and the following five postoperative days with clinical evaluation every 2 hs. Following initial evaluation of 124 cases, we modified our postoperative monitoring scheme toward a shorter monitoring period. After performance of further 100 free flaps, outcomes of the two monitoring schemes were analyzed in depth and compared retrospectively.</div></div><div><h3>Results</h3><div>Eighty-nine percent of complications with the need of revision occurred within the operation day and the following 3 ds postoperatively. Total flap loss was 6.5%. Flap salvage rates after revision were 50-80% in this period. Flaps that had a later revision could not be saved (<em>n</em> = 2). The optimized monitoring protocol includes a clinical examination on the day of surgery and for the three postoperative days. In the event of intraoperative complications, the senior surgeon could extend postoperative monitoring to five postoperative days, which was decided for in four cases. After optimizing the protocol, total flap loss was 3%. Flap salvage rates after revision varied between 33% and 100%.</div></div><div><h3>Conclusions</h3><div>Flap monitoring is crucial for maximizing the salvage rate in microsurgical reconstruction. Optimizing our monitoring protocol toward a shorter postoperative monitoring period in our cohort did not lead to an increased complication rate while saving resources.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"307 ","pages":"Pages 1-7"},"PeriodicalIF":1.8,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143177753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preferences for Inguinal Hernia Repair in Infants: A Survey of the Eastern Pediatric Surgery Network","authors":"Zane J. Hellmann MD ,&nbsp;J. Leslie Knod MD ,&nbsp;Afif N. Kulaylat MD ,&nbsp;Cornelia Griggs MD ,&nbsp;Jennifer R. DeFazio MD ,&nbsp;Stefan Scholz MD ,&nbsp;Hanna Alemayehu MD ,&nbsp;Jamie R. Robinson MD, PhD ,&nbsp;Shaun M. Kunisaki MD, MSc ,&nbsp;Matthew A. Hornick MD","doi":"10.1016/j.jss.2024.12.012","DOIUrl":"10.1016/j.jss.2024.12.012","url":null,"abstract":"<div><h3>Introduction</h3><div>Laparoscopic inguinal hernia repair (IHR) is being performed more frequently in children, but few studies have evaluated surgical practice patterns in infants. In this study, we surveyed pediatric surgeons within a regional consortium to assess current preferences for IHR strategy in infants. We hypothesized that early-career pediatric surgeons would prefer laparoscopic IHR over open IHR in this patient population.</div></div><div><h3>Methods</h3><div>A Qualtrics survey addressing surgeon preferences for IHR was distributed to 160 pediatric surgeons at 19 member institutions affiliated with the Eastern Pediatric Surgery Network. Surgeons were stratified by self-reported number of years in attending practice. Responses were compared using <em>t</em>-tests and chi-square tests wherever appropriate.</div></div><div><h3>Results</h3><div>Ninety-eight surgeons responded to the survey (61% response rate; two incomplete responses were excluded). Forty respondents (41.7%) had 0-10 ys of experience, 26 (27.1%) had 10-20 ys of experience, and 30 (31.2%) had over 20 ys of experience. Over 90% of early-career surgeons reported a preference for laparoscopic IHR in infants, compared to less than 50% of mid-career surgeons and less than 20% of late-career surgeons (<em>P</em> &lt; 0.001). Respondents preferring laparoscopic IHR most commonly cited inherent assessment of the contralateral side, confirmation of hernia before repair, and technical ease of the laparoscopic approach as factors contributing to their preference.</div></div><div><h3>Conclusions</h3><div>The majority of early-career pediatric surgeons prefer laparoscopic IHR over open IHR in infants, representing a substantial shift away from what is traditionally regarded as the gold standard open technique. Larger studies are needed to compare long-term outcomes after laparoscopic and open IHR in infants.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"306 ","pages":"Pages 188-196"},"PeriodicalIF":1.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142965586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Disparities in Rehabilitation Services for Victims of Violence","authors":"Megan G. Janeway MD ,&nbsp;Ella Cornell MD ,&nbsp;Sophia M. Smith MD, MS ,&nbsp;Anne K. Buck MS ,&nbsp;Miriam Neufeld MD, MPH ,&nbsp;Janice Weinberg ScD ,&nbsp;Stephanie D. Talutis MD, MPH ,&nbsp;Nina Jreige MD ,&nbsp;Victoria Liang MD ,&nbsp;Timothy Munzert MSW, LICSW ,&nbsp;Tracey Dechert MD, FACS ,&nbsp;Sabrina E. Sanchez MD, MPH ,&nbsp;Lisa Allee MSW, LICSW","doi":"10.1016/j.jss.2024.12.040","DOIUrl":"10.1016/j.jss.2024.12.040","url":null,"abstract":"<div><h3>Introduction</h3><div>Access to rehabilitation services after a traumatic injury improves functional outcomes. No study has examined the association between injury intent, violent <em>versus</em> nonviolent, and receipt of rehabilitation services after injury.</div></div><div><h3>Materials and methods</h3><div>We conducted a retrospective cohort study of injured adult patients admitted to our level I trauma center from January 1, 2014 to December 31, 2021. The primary exposure was violent injury, and the primary outcome was receipt of rehabilitation services upon discharge. An exploratory subgroup analysis evaluated differences in recommended disposition and the reasons for rejection from services.</div></div><div><h3>Results</h3><div>Among 7500 patients, 1677 (22.4%) were violently injured and 5823 (77.6%) were nonviolently injured. Patients were 45% White, 67% male, and 52% had public insurance. Adjusting for age, sex, race, ethnicity, injury severity score, insurance, and length of stay, violently injured patients were 77% less likely to receive inpatient rehabilitation (relative risk ratio 0.23 95% confidence interval [0.18, 0.30], <em>P</em> &lt; 0.001) and 46% less likely to have home services (relative risk ratio 0.54, 95% confidence interval[0.43, 0.69], <em>P</em> &lt; 0.001). A subgroup analysis (<em>n</em> = 328) demonstrated that violently injured patients were more likely to have a downgrade in discharge recommendation (27.8% <em>versus</em> 9.4%, <em>P</em> = 0.04) and more likely to have an emergency department visit within 30 d (32.0% <em>versus</em> 13.3%, <em>P</em> &lt; 0.001).</div></div><div><h3>Conclusions</h3><div>Violent injury is associated with lower likelihood of receiving rehabilitation services. Subgroup analysis indicates this finding associated with facilities’ selection bias, and this warrants additional study. Efforts should focus on protecting victims of violence from discrimination during the rehabilitation screening process.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"306 ","pages":"Pages 317-326"},"PeriodicalIF":1.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143023859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rare Rib-Originating Solitary Plasmacytoma: Retrospective Analysis and Surgical Outcomes","authors":"Sevinc Citak MD ,&nbsp;Serkan Bayram MD ,&nbsp;Busra Yaprak Bayrak MD ,&nbsp;Mustafa Vayvada MD ,&nbsp;Cagatay Tezel MD","doi":"10.1016/j.jss.2024.12.054","DOIUrl":"10.1016/j.jss.2024.12.054","url":null,"abstract":"<div><h3>Introduction</h3><div>Solitary plasmacytomas are tumors characterized by a local increase of malignant plasma cells in soft tissue or bone and may occur anywhere without evidence of systemic disease. The aim was to focus on the main surgical techniques and outcomes for this rare chest wall tumor.</div></div><div><h3>Methods</h3><div>Patients with solitary plasmacytoma involving a rib, who were operated for diagnostic or treatment purposes between 2018 and 2023 were retrospectively reviewed.</div></div><div><h3>Results</h3><div>Of the six patients included, three were male and the median age was 55.6 (range: 32-74) ys. All patients had preoperative positron emission tomography-computed tomography. Two underwent Tru-cut biopsy before surgery, but only one was then diagnosed. Two patients underwent surgery for diagnosis and the remainder underwent resection and reconstruction. In one patient with both rib and sternum involvement, rib and partial sternum resection was performed and the defect was repaired with mesh. During the 24.1 mos average follow-up period, two patients died, both of whom had metastasis preoperatively. The median survival of all patients was 24.1 (range: 3-63) mos.</div></div><div><h3>Conclusions</h3><div>Solitary plasmacytoma is rarely seen among primary malign tumors of the chest wall. A multidisciplinary approach is important in these cases. Surgical treatment in solitary plasmacytoma has fewer local and systemic side effects compared to radiotherapy and chemotherapy. Therefore, the place of surgery in the treatment of solitary plasmacytoma should be revised. Our findings show that surgery should be considered as not only a palliative treatment, but also a curative one, in solitary plasmacytomas arising in the rib.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"306 ","pages":"Pages 417-423"},"PeriodicalIF":1.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143033321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Forecasting Pediatric Trauma Volumes: Insights From a Retrospective Study Using Machine Learning","authors":"Ayaka Tsutsumi MD ,&nbsp;Chiara Camerota PhD ,&nbsp;Flavio Esposito PhD ,&nbsp;Si-Min Park MD ,&nbsp;Tiffany Taylor MSN, MBA, RN ,&nbsp;Shin Miyata MD","doi":"10.1016/j.jss.2024.12.010","DOIUrl":"10.1016/j.jss.2024.12.010","url":null,"abstract":"<div><h3>Introduction</h3><div>Rising pediatric firearm-related fatalities in the United States strain Trauma Centers. Predicting trauma volume could improve resource management and preparedness, particularly if daily forecasts are achievable. The aim of the study is to evaluate various machine learning models’ accuracy on monthly, weekly, and daily data.</div></div><div><h3>Methods</h3><div>The retrospective study utilized trauma data between June 1, 2013, and October 31, 2023, from a level I/II pediatric trauma center. Data were organized monthly, weekly, and daily, which further delineated into seven groups, yielding 21 cohorts. Models were evaluated using time-series forecasting metrics. In addition, the models were tested for real-world applicability by forecasting trauma volumes 3 mo, 12 wk, and 31 d ahead for monthly, weekly, and daily predictions respectively. The predicted values were then compared with the actual data.</div></div><div><h3>Results</h3><div>The total of 12,144 patients’ data was utilized to create and evaluate models. 14 forecasting models for each of 21 groups were developed. Monthly predictions generally outperformed weekly and daily ones. Although the Silverkite model excelled in monthly predictions, the one-dimensional convolutional layer model was most accurate for daily predictions. Real-life simulations showed the Prophet model performing best for monthly predictions, with no clear winner for weekly predictions.</div></div><div><h3>Conclusions</h3><div>This study found monthly forecasting most accurate. Although many models outperformed their Naïve counterparts, performance varied by grouping. Real-world simulations confirmed these findings. Despite high accuracy in monthly predictions, the study's generalizability is limited, and daily trauma prediction needs improvement.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"306 ","pages":"Pages 33-42"},"PeriodicalIF":1.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142915087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using Machine Learning to Predict Weight Gain in Adults: an Observational Analysis From the All of Us Research Program","authors":"Dawda Jawara MD ,&nbsp;Kate V. Lauer MD ,&nbsp;Manasa Venkatesh MS ,&nbsp;Lily N. Stalter MS ,&nbsp;Bret Hanlon PhD ,&nbsp;Matthew M. Churpek MD, MPH, PhD ,&nbsp;Luke M. Funk MD, MPH","doi":"10.1016/j.jss.2024.11.042","DOIUrl":"10.1016/j.jss.2024.11.042","url":null,"abstract":"<div><h3>Introduction</h3><div>Obesity, defined as a body mass index ≥30 kg/m², is a major public health concern in the United States. Preventative approaches are essential, but they are limited by an inability to accurately predict individuals at highest risk of weight gain. Our objective was to develop accurate weight gain prediction models using the National Institutes of Health All of Us dataset. We hypothesized that machine learning models using both electronic health record and behavioral survey data would outperform models using electronic health record data alone.</div></div><div><h3>Methods</h3><div>The All of Us dataset was used to identify adults between 18 and 70 ys old with weight measurements 2 y apart between 2008 and 2022. Patients with a history of cancer, bariatric surgery, or pregnancy were excluded. Demographics, vital signs, laboratory results, comorbidities, and survey data (Alcohol Use Disorder Identification Test, Patient-Reported Outcomes Measurement Information System physical and mental health scores) were included as model parameters. Elastic net and XGBoost machine learning models were developed with and without survey data to predict ≥10% total body weight gain within 2 y. The data were split into a training sample (60%) and a testing sample (40%), and parameters were tuned using 10-fold cross-validation. Performance was compared using area under the receiver operating characteristic curves (AUCs).</div></div><div><h3>Results</h3><div>Our cohort consisted of 34,715 patients (mean [SD] age 50.9 [13.4] y; 45.7% White; 55.3% female). Over a 2-y span, 10.4% of the cohort gained ≥10% total body weight. AUCs were 0.677 [95% DeLong confidence interval 0.665-0.688] for elastic net and 0.706 [0.695-0.717] for XGBoost. Incorporation of survey data did not improve predictability, with AUCs of 0.681 [0.669-0.692] and 0.705 [0.694-0.716], respectively.</div></div><div><h3>Conclusions</h3><div>Our machine learning weight gain prediction models had modest performance that was not improved by survey data. The addition of other All of Us variables, including genomic data, may be informative in future studies.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"306 ","pages":"Pages 43-53"},"PeriodicalIF":1.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142915214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}