Search

BACKGROUND Hospitals are struggling in predicting, evaluating and managing various cost-affecting parameters pertaining to any given patient and their treatments. Accuracy in cost prediction is a challenge and is further affected if a patient suffers from other health issues which complicate their primary diagnosis and negatively impact prognosis. The inability to appropriately predict the cost of care can lead to an unavoidable deficit in the operational revenue of medical centers. OBJECTIVE This study aims to determine whether machine learning (ML) algorithms can predict the cost of care in patients undergoing bariatric and metabolic surgery as well as to develop and validate a predictive model for bariatric and metabolic surgery that allows for better management and optimization of cost analysis faced by hospital administration. METHODS A total of 602 patients are included in our study. This includes all patients from Wetzikon hospital that underwent bariatric and metabolic surgery from 2013-2019. Multiple variables, including patient factors, surgical factors, and post-operative complications were tested using a number of predictive modeling strategies to deliver on a tool that may be helpful for hospitals in forecasting and managing costs associated with the delivery of care. The registry data was approved by an institutional review board, where the patients’ informed consent was waived. The study was registered under Req 2022-00659. The overall cost to the hospital is defined as the sum of all the costs incurred during the stay in hospital for surgery, expressed in CHF (Swiss Francs). This data was collected from the financial administrative system of Wetzikon Hospital. After preprocessing, the cost is randomly split into two sets. 80% of the data is put into a training set to build the models and 20% is utilized for a test set to validate the models and assess their performance. Hyperparameters are tuned, and the final model is selected based on the mean absolute percentage error (MAPE). RESULTS Out of the six tested models, the results obtained based on analysis showed that the Random Forest model is the most accurate at predicting overall cost associated with bariatric and metabolic surgery. With a mean absolute percentage error of 12.7 – 26.3, we have demonstrated a model with reasonable prediction to be validated in real-world scenarios. CONCLUSIONS This model may therefore be considered by hospitals to help with financial calculations and balancing the budget, however, further research should be undertaken to improve its accuracy. This model can ultimately lead to cost-efficient operation and administration of hospitals. The proof of principle demonstrated here will lay the groundwork for an efficient ML-based prediction tool to be tested on multicenter data from a range of international centers in the subsequent phases of the study.

Purpose Neuropathic pain is a complication after groin hernia surgery. Triple neurectomy of the iliohypogastric nerve, ilioinguinal nerve and genitofemoral nerve is an efficient treatment modality, with several surgical approaches. The minimally invasive endoscopic method to neurectomy was specifically investigated in this meta-analysis. Our aim is to determine the efficacy of this method in the treatment of chronic neuropathic pain posthernia repair surgery. Methods A systematic review was conducted using four databases to search for the keywords (“endoscopic retroperitoneal neurectomy” and “laparoscopic retroperitoneal neurectomy”). The NCBI National Library of Medicine, Cochrane Library, MEDLINE Complete and BioMed Central were last searched on 26 May 2022. Randomised control trials and retrospective or prospective papers involving endoscopic retroperitoneal neurectomy operations after inguinal hernia repair were included. All other surgeries, procedures and study designs were excluded. The internal quality of included studies was assessed using the Newcastle–Ottawa Scale. The percentage of patients who had reduction in pain (“positive treatment outcome”) was used to assess the procedure’s effectiveness in each analysis. Results Five comparable endoscopic retroperitoneal neurectomy studies with a total of 142 patients were analysed. Both the Wald test (Q (6) = 1.79, = .775) and the probability ratio test (Q (6) = 4.24, = .374) provide similar findings (0.000, 0.0% [0.0%; 78%]). The meta-analysis’ key finding is that the intervention was up to 78% effective (95% confidence interval, 71%; 84%). Conclusion Endoscopic retroperitoneal neurectomy can be an effective treatment option for postoperative neuropathic pain relief following surgical hernia repair. Although there is limited reported experience with this technique, it may provide a clinical benefit to the patient. We recommend further prospective data and long-term follow-up studies be conducted to confirm and expand on these outcomes.

Background: Complications in colon surgery can have severe health consequences, while at the same time, they are associated with increased costs. An anastomotic leak (AL) is associated with significantly increased costs compared to cases without. The aim of our analysis was to evaluate, which individual processes and patient-unrelated factors influencing the treatment process of colon surgery are responsible for the financial burden in patients with AL. Methods: Data from 263 patients who underwent colon surgery in Wetzikon hospital between January 2018 and December 2020 and was analyzed. In these 263 cases, 12 anastomotic leaks occurred and were compared with 36 cases without AL using a Propensity Score Matching (PSM). The covariates for the PSM have been Age, Sex, and Type of Surgery (t value: −3.26, p-value: 0.001). Results: A total of 48 surgeries were broken down in terms of costs and profitability. This reflected a mean deficit of −37,527 CHF per case (range from −130.05 to +755 CHF) for patients with AL, whereas a mean profit of 1590 CHF per case (range from −24.37 to +12.65 CHF) for those without AL (p < 0.001). Thus, the difference in profit showed a factor of 24.6 with an overall significant negative outcome for the occurrence of AL. The main cost contributing factors were the length of hospital stay (~p < 0.05) and length of intensive care (p < 0.05), whereas neither surgical operation time and anesthesia time nor surgical access, insurance status, indication or type of operation had a significant influence on the net revenue. Conclusion: AL after colon surgery leads to a significant deficit regarding the net revenue. Regarding process optimization, our analysis identified several sectors of non-patient-related, yet cost-influencing variables that should be addressed in future evaluations and optimization of the colon surgery treatment processes.

Background The primary goal of this study is to assess the current patient information available on the internet concerning robotic colorectal surgery. The study is a review, and acquiring this information is relevant to understanding the subject's current and future scope. Methods We acquired data for this study through a web-scraping algorithm. The algorithm used two Python packages: Beautiful Soup and Selenium. The long-chain keywords incorporated into the Google, Bing and Yahoo search engines for this study were "Da Vinci Colon-Rectal Surgery", “Colorectal Robotic Surgery” and “Robotic Bowel Surgery”. After sorting the 207 websites, 5 investigators evaluated the websites according to the Ensuring quality information for patients (EQIP) score. Results Of the 207 websites visited, 49 belonged to the subgroup of hospital websites (23.6%), 46 to Medical Centers (22.2%), 45 to Practitioners (21.7%), 42 to Health Care Systems (20,2%), 11 to News Services (5.3%), 7 to Web Portals (3.3%), 5 to the Industry (2.4%), and 2 to Patient Groups (0.9%). Conclusion The quality of the information available on the internet concerning robotic colorectal surgery is low since only 82 websites received a high rating. Most of the information on the different websites is inaccurate, consequently medical facilities involved in robotic colorectal surgery, robotic bowel surgery and related should develop credible websites to guide patient decisions.

IntroductionPsychiatric and psychosomatic diseases are an increasingly cumbersome burden for the medical system. Indeed, hospital costs associated with mental health conditions have been constantly on the rise in recent years. Moreover, psychiatric conditions are likely to have a negative effect on the treatment of other medical conditions and surgical outcomes, in addition to their direct effects on the overall quality of life. Our study aims to investigate the impact of preoperative risk factors, psychiatric and psychosomatic diseases, and non-psychiatric and non-psychosomatic diseases on the outcomes of small and large bowel surgery and length of hospital stay via predictive modeling techniques.Methods and AnalysisPatient data will be collected from several participating national and international surgical centers. The machine learning models will be calculated and coded, but also published in respect to the TRIPOD guidelines (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis).Expected ResultsIt is conceivable to arrive at generalizable models predicting the above-mentioned endpoints through large amounts of data from several centers. The models will be subsequently deployed as a free-to-use web-based prediction tool.Ethics and DisseminationThe ethical is approved by Cantonal Ethics Committee Zurich, Switzerland BASEC Nr. 2021-02105.

Hospitals are burdened with predicting, calculating and managing various cost-affecting parameters regarding patients and their treatments. Accuracy in cost prediction is further affected if a patient suffers from other health issues which hinder the traditional prognosis. This can lead to an unavoidable deficit in the final revenue of medical centers. This study aims to determine whether machine learning (ML) algorithms can predict cost factors based on patients undergoing colon surgery. For the forecasting, multiple predictors will be taken into the model to provide a tool that can be helpful for hospitals to manage their costs which ultimately will lead to operating more cost-efficiently.. This proof of principle will lay the groundwork for an efficient ML-based prediction tool based on multicenter data from a range of international centers in the subsequent phases of the study. With a % MAPE result of 18 – 25.6, our model’s prediction showed decent results to forecast the costs regarding various diagnosed factors and surgical approaches. There is an urgent need for further studies on predicting cost factors, especially for cases with anastomotic leakage, to minimize unnecessary costs for hospitals.

Objective: The use of machine learning (ML) has revolutionized every domain of medicine. Surgeons are now using ML models for disease detection and outcome prediction with high precision. ML-guided colorectal surgeries are more efficient than conventional surgical procedures. The primary aim of this paper is to provide an overview of the latest research on “ML in colorectal surgery”, with its viable applications. Methods: PubMed, Google Scholar, Medline, and Cochrane library were searched. Results: After screening, 27 articles out of 172 were eventually included. Among all of the reviewed articles, those found to fit the criteria for inclusion had exclusively focused on ML in colorectal surgery, with justified applications. We identified existing applications of ML in colorectal surgery. Additionally, we discuss the benefits, risks, and safety issues. Conclusions: A better, more sustainable, and more efficient method, with useful applications, for ML in surgery is possible if we and data scientists work together to address the drawbacks of the current approach. Potential problems related to patients’ perspectives also need to be resolved. The development of accurate technologies alone will not solve the problem of perceived unreliability from the patients’ end. Confidence can only be developed within society if more research with precise results is carried out.

IntroductionAnastomotic insufficiency (AI) is a relatively common but grave complication after colorectal surgery. This study aims to determine whether AI can be predicted from simple preoperative data using machine learning (ML) algorithms.Methods and analysisIn this retrospective analysis, patients undergoing colorectal surgery with creation of a bowel anastomosis from the University Hospital of Basel were included. Data was split into a training set (80%) and a test set (20%). The group of patients with AI was oversampled to a ratio of 50:50 in the training set and missing values were imputed. Known predictors of AI were included as inputs: age, BMI, smoking status, the Charlson Comorbidity Index, the American Society of Anesthesiologists score, type of operation, indication, haemoglobin and albumin levels, and renal function.ResultsOf the 593 included patients, 88 experienced AI. At internal validation on unseen patients from the test set, area under the curve (AUC) was 0.61 (95% confidence interval [CI]: 0.44-0.79), calibration slope was 0.16 (95% CI: −0.06-0.39) and calibration intercept was 0.06 (95% CI: 0.02-0.11). We observed a specificity of 0.67 (95% CI: 0.58-0.76), sensitivity of 0.36 (95% CI: 0.08-0.67), and accuracy of 0.64 (95% CI: 0.55-0.72).ConclusionBy using 10 patient-related risk factors associated with AI, we demonstrate the feasibility of ML-based prediction of AI after colorectal surgery. Nevertheless, it is crucial to include multicenter data and higher sample sizes to develop a robust and generalisable model, which will subsequently allow for deployment of the algorithm in a web-based application.Strengths and limitations of this studyTo the best of our knowledge, this is the first study to establish a risk prediction model for anastomotic insufficiency in a perioperative setting in colon surgery.Data from all patients that underwent colon surgery within 8 years at University Hospital Basel were included.We evaluated the feasibility of developing a machine learning model that predicts the outcome by using well-known risk factors for anastomotic insufficiency.Although our model showed promising results, it is crucial to validate our findings externally before clinical practice implications are possible.

Background: This study aimed to compare property development and increasing investment in real estate by the healthcare system organizations in the USA and Europe. Real estate investments have upsurged in healthcare due to the multiple benefits to patients and medical practitioners. Methods: The approach of acquiring data was through secondary sources and online questionnaires. The researchers applied inclusion and exclusion criteria by exclusively including the articles published after 2014 to ensure the validity and reliability of the information. Results: A total of 53.33% of the articles reviewed focused on the United States, while 46.67% concentrated on Europe. The development of real estate in healthcare is essential in both regions due to the challenges faced with the current infrastructure. Study Limitation: Currently, there are very few studies concentrating on the research topic. Conclusions: The USA and Europe should focus on increasing real estate investments in healthcare by focusing on hospitals and trusts, rehabilitation centers, and nursing homes.

Background: Ventral hernia repairs (VHR) are frequent but loss- making. This study aims to identify epidemiological and procedure related factors in VHR and their influence on surgical training. Methods: Data from 86 consecutive patients who underwent VHR in 2019 was collected. Moreover, 66 primary ventral hernias and 20 incisional hernias were repaired in open procedures. Linear regression models were made. Results: Primary VHR procedures showed a mean deficit of −378.17 CHF per case. Incisional hernia repair procedures resulted in a deficit of −1442.50 CHF per case. The two hernia groups were heterogeneous. For the primary VHR procedures, the surgery time (β = 0.564, p &lt, 0.001) had the greatest influence, followed by the costs of the mesh (β = −0.215, p &lt, 0.001). The epidemiological factors gender (β = 0.143, p &lt, 0.01) and body mass index (BMI) (β = −0.087, p = 0.074) were also influential. For incisional hernia procedures a surgeon’s experience had the most significant influence (β = 0.942, p &lt, 0.001), and the second largest influence was the price of the mesh (β = -.500, p &lt, 0.001). The epidemiological factor BMI (β = −0.590, p &lt, 0.001), gender (β = −0.113, p = 0.055) and age (β = −0.026, p &lt, 0.050) also had a significant influence. Conclusion: Our analysis shows a way of improving financial results in the field of ventral hernia repair. Costs can be visualized and reduced to optimize revenue enhancement in surgical departments. In our analysis primary ventral hernias are an appropriate training operation, in which the experience of the surgeon has no significant impact on costs. In primary VHR procedures, revenue enhancement is limited when using an expensive mesh. However, the treatment of incisional hernias is recommended by specialists. The financial burden is significantly higher with less experience. Therefore, these operations are not suitable for surgical training. The re-operation rate decreases with increasing experience of the surgeon. This directly affects the Patient Related Outcome (PROM) and quality of treatment. Therefore, high-quality training must be enforced. Since financial pressure on hospitals is increasing further, it is crucial to investigate cost influencing factors. The majority of Swiss public hospitals will no longer be able to operate ventral hernias profitably without new concepts. In addition to purchasing management, new construction projects, and mergers, improving the results of individual departments is a key factor in maintaining the profitability of hospitals in the future regarding hernia repair without losing the scope of teaching procedures.

Oncostatin M is a novel growth regulator originally isolated from differentiated human histiocytic lymphoma cells and activated T-lymphocytes based on its ability to inhibit the growth of A375 melanoma cells. We report here that oncostatin M is a widely acting regulator which alters the growth and/or morphology of cells derived from a variety of cancer cell types. At picomolar concentrations, recombinant oncostatin M inhibited the growth of 13/24 tumor cell lines. Six out of 7 lung cancer cell lines were inhibited by oncostatin M, but none of 6 colon cancer cell lines were affected. Oncostatin M also stimulated the growth of some normal cells (3/6), indicating that it, like many growth regulators, is bifunctional. Oncostatin M receptors appear necessary but not sufficient for a growth response to oncostatin M, since none of the cell lines lacking receptor responded to oncostatin M, whereas many but not all cell lines with receptor responded to oncostatin M. Receptor size (Mr congruent to 150,000) was similar for cells in which growth was inhibited, stimulated, or unaffected by oncostatin M.

Oncostatin M is a polypeptide of Mr approximately 28,000 that acts as a growth regulator for many cultured mammalian cells. We report the cDNA and genomic cloning, sequence analysis, and functional expression in heterologous cells of oncostatin M. cDNA clones were isolated from mRNA of U937 cells that had been induced to differentiate into macrophagelike cells by treatment with phorbol 12-myristate 13-acetate, and a genomic clone was also isolated from human brain DNA. Sequence analysis of these clones established the 1,814-base-pair cDNA sequence as well as exon boundaries. This sequence predicted that oncostatin M is synthesized as a 252-amino-acid polypeptide, with a 25-residue hydrophobic sequence resembling a signal peptide at the N terminus. The predicted oncostatin M amino acid sequence shared no homology with other known proteins, but the sequence of the 3' noncoding region of the cDNA contained an A + T-rich stretch with sequence motifs found in the 3' untranslated regions of many cytokine and lymphokine cDNAs. Oncostatin M mRNA of approximately 2 kilobase pairs was detected in phorbol 12-myristate 13-acetate-treated U937 cells and in activated human T cells. Transfection of cDNA encoding the oncostatin M precursor into COS cells resulted in the secretion of proteins with the structural and functional properties of oncostatin M. The unique amino acid sequence, expression by lymphoid cells, and growth-regulatory activities of oncostatin M suggest that it is a novel cytokine.

The murine anti-human lung tumor monoclonal antibody L3 recognizes antigens found both in the medium of cultured carcinoma cells and in normal human serum. Sequential immunoprecipitation experiments indicate that the L3 antigen is also recognized by a previously described monoclonal antibody directed against a melanoma-associated antigen [Natali, P. G., Wilson, B. S., Imai, K., Bigotti, A., & Ferrone, S. (1982) Cancer Res. 42, 583-589]. This antibody precipitated a Mr 76000 glycoprotein from metabolically labeled extracts of the lung carcinoma cell line Calu-1 and a Mr 94 000 glycoprotein from labeled culture medium. Pulse-chase experiments suggested a precursor-product relationship between these molecules. Analysis of glycosidase sensitivities of the two forms indicated that maturation of carbohydrate side chains correlated with the apparent increase in molecular weights. L3 antigenic activity, measured in a competitive radiometric cell binding assay, was purified more than 90-fold from serum-free medium of Calu-1 cells and more than 3000-fold from normal human serum. The major immunoreactive components purified from culture medium and serum were identical with respect to apparent molecular weight, electrophoretic mobility, pI, glycosidase sensitivity, and V8 protease fingerprints. In addition, the sequence of the amino-terminal 16 N-terminal amino acid residues of the major immunoreactive species from both sources was identical. The properties of the L3 antigen did not correspond to those of any known protein, suggesting that this serum protein has not been previously characterized.