RESUMEN

BACKGROUND: The pilot study addresses the challenge of predicting postoperative outcomes, particularly body mass index (BMI) trajectories, following bariatric surgery. The complexity of this task makes preoperative personalized obesity treatment challenging. OBJECTIVES: To develop and validate sophisticated machine learning (ML) algorithms capable of accurately forecasting BMI reductions up to 5 years following bariatric surgery aiming to enhance planning and postoperative care. The secondary goal involves the creation of an accessible web-based calculator for healthcare professionals. This is the first article that compares these methods in BMI prediction. SETTING: The study was carried out from January 2012 to December 2021 at GZOAdipositas Surgery Center, Switzerland. Preoperatively, data for 1004 patients were available. Six months postoperatively, data for 1098 patients were available. For the time points 12 months, 18 months, 2 years, 3 years, 4 years, and 5 years the following number of follow-ups were available: 971, 898, 829, 693, 589, and 453. METHODS: We conducted a comprehensive retrospective review of adult patients who underwent bariatric surgery (Roux-en-Y gastric bypass or sleeve gastrectomy), focusing on individuals with preoperative and postoperative data. Patients with certain preoperative conditions and those lacking complete data sets were excluded. Additional exclusion criteria were patients with incomplete data or follow-up, pregnancy during the follow-up period, or preoperative BMI ≤30 kg/m2. RESULTS: This study analyzed 1104 patients, with 883 used for model training and 221 for final evaluation, the study achieved reliable predictive capabilities, as measured by root mean square error (RMSE). The RMSE values for three tasks were 2.17 (predicting next BMI value), 1.71 (predicting BMI at any future time point), and 3.49 (predicting the 5-year postoperative BMI curve). These results were showcased through a web application, enhancing clinical accessibility and decision-making. CONCLUSION: This study highlights the potential of ML to significantly improve bariatric surgical outcomes and overall healthcare efficiency through precise BMI predictions and personalized intervention strategies.

RESUMEN

Hospitals are facing difficulties in predicting, evaluating, and managing cost-affecting parameters in patient treatments. Inaccurate cost prediction leads to a deficit in operational revenue. This study aims to determine the ability of Machine Learning (ML) algorithms to predict the cost of care in bariatric and metabolic surgery and develop a predictive tool for improved cost analysis. 602 patients who underwent bariatric and metabolic surgery at Wetzikon hospital from 2013 to 2019 were included in the study. Multiple variables including patient factors, surgical factors, and post-operative complications were tested using a number of predictive modeling strategies. The study was registered under Req 2022-00659 and approved by an institutional review board. The cost was defined as the sum of all costs incurred during the hospital stay, expressed in CHF (Swiss Francs). The data was preprocessed and split into a training set (80%) and a test set (20%) to build and validate models. The final model was selected based on the mean absolute percentage error (MAPE). The Random Forest model was found to be the most accurate in predicting the overall cost of bariatric surgery with a mean absolute percentage error of 12.7. The study provides evidence that the Random Forest model could be used by hospitals to help with financial calculations and cost-efficient operation. However, further research is needed to improve its accuracy. This study serves as a proof of principle for an efficient ML-based prediction tool to be tested on multi-center data in future phases of the study.

Asunto(s)

RESUMEN

BACKGROUND: Laparoscopic local excision is accepted for gastrointestinal stromal tumors (GIST) and benign lesions of the stomach. Yet, tumors at the gastroesophageal junction, on the posterior wall, or in the distal antrum are difficult to approach. Such tumors often must be exposed via gastrotomy or using a rendezvous maneuver. Our method of total intragastric laparoscopic resection using 'pneumogastrum', rigid laparoscope, and conventional laparoscopic instruments is described in an intuitive video. METHODS: Two cases of total inverse transgastric resection involved resection of a submucosal GIST, one at the front wall of the cardia and the other on the posterior wall of the antrum. The third case required excision of a large prepyloric cystic lesion leading to a gastric outlet stenosis. After insertion of three trocars under laparoscopic control, a further trocar was introduced into the stomach and 'pneumogastrum' was established. Two additional 5-mm trocars were intragastrally placed. Intragastric endoscopy with a rigid optic provided an excellent view. The tumor was exposed resected with a linear stapler. The specimen was inserted into an Endo Pouch™ which was sutured to an orally inserted gastric tube. The Endo Pouch™ was gently pulled transorally. After removal of the intragastric trocars, the entrance points were laparoscopically closed. RESULTS: From the first and second cases, we retrieved GIST tumors. In the third case, we retrieved a gastritis cystica profunda. Postoperative course was uneventful. CONCLUSIONS: Gastric GIST should be resected laparoscopically if negative margins are safely achieved regardless of its size. Tumors at the frontwall and exophytic backwall GIST are addressed by laparoscopic wedge resection. Tumors at the gastrojejunal junction, in the prepyloric region, and fundus as well as submucous GIST of the gastric backwall are best approached by intragastric laparoscopic resection. Transoral specimen retrieval is an interesting option in smaller tumors.

Asunto(s)

RESUMEN

The long-term rotatory stability of meniscus suture repair has not been firmly established clinically. Up to now there are only experimental studies done. This retrospective study aimed to compare the long-term rotatory stability of a knee with a meniscus suture repair with the stability of the uninjured knee in each of a cohort of patients. We evaluated both knees of 64 patients at an average follow-up of 11 years (range : 5 to 17) after successful arthroscopic meniscus suture repair. Each patient's injury was an isolated longitudinal-vertical meniscus tear and each patient's opposite knee was uninjured. All repairs were performed with the same outside in meniscus suture repair technique. Evaluation included standardised clinical examination, anterior stability testing with a ligament testing device, and rotational testing with a rotational laxiometer. In the stability assessments, the mean anteroposterior translation was the same for repaired and uninjured knees: 3 mm at 67 N and 5 mm at 89 N. The mean external rotation was the same in repaired knees and uninjured knees at 20 degrees of flexion (22 degrees) and similar in repaired knees (22 degrees) and uninjured knees (23 degrees) at 90 degrees flexion. The mean internal rotation was similar in repaired knees (12 degrees) and uninjured knees (13 degrees) at 20 degrees and 90 degrees of flexion. Our findings indicate that a knee with arthroscopic meniscus suture repair displays a rotational stability that is equal to or nearly equal to the stability of an uninjured knee. However, whether rotational stability will only be preserved due to meniscus repair and how much of the meniscus needs to be preserved in order to maintain the biomechanical stability of the knee remains unclear.

Asunto(s)

RESUMEN

BACKGROUND: The long-term outcome of meniscal suture repair has not been firmly established. PURPOSE: To compare the midterm and long-term functional and radiographic outcome of meniscal suture repairs with the natural history of the uninjured knees of each of a cohort of patients. STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: Eighty-eight patients with an isolated, longitudinal, vertical tear of one of the menisci within a stable knee were arthroscopically treated with a meniscal suture repair. No patient had a previous surgery, and no additional chondral lesion was present. The opposite knee of each patient was uninjured. Both knees of each patient were examined clinically and radiographically in a retrospective follow-up 5 to 17 years (mean, 10 years) after meniscal repair. RESULTS: Three patients with postoperative complications and 21 patients whose menisci had to be removed because of rerupture were excluded from further evaluation for purposes of this study. The remaining 64 patients reached a mean Tegner activity level of 6 points (range, 3-10 points) and achieved a mean Lysholm score of 94 points (range, 26-100 points). Osteoarthritis was found in 46 of the injured knees, compared with 27 of the uninjured knees (P = .004). However, 42 of the patients had no difference in the grade of osteoarthritis between the injured knee and the uninjured knee, 19 had a difference of 1 grade, 2 had a difference of 2 grades, and 1 had a difference of 3 grades. CONCLUSION: Arthroscopic meniscal repair for isolated longitudinal meniscal injuries in stable knees yields favorable functional results, but its effects on the risk of secondary osteoarthritis are not clear.

Asunto(s)