Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree
Ontology highlight
ABSTRACT:
SUBMITTER: Wakiya T
PROVIDER: S-EPMC8577735 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Objectives/hypothesisThe purpose of this study is to improve patient understanding of surgical outcomes while they make a preference-sensitive decision regarding electing endoscopic sinus surgery (ESS) for chronic rhinosinusitis (CRS).Study designProspective observational cohort study.MethodsPatients with CRS who elected ESS were prospectively enrolled into a multi-institutional, observational cohort study. Patients' were categorized into 10 preoperative Sino-Nasal Outcome Test (SNOT-22) groups based on 10-point increments beginning with a score of 10 and ending at 110. The proportion of patients achieving a SNOT-22 minimal clinically important difference (MCID) (9 points) and the percentage of relative improvement (%) for each preoperative SNOT-22 group were calculated. A subgroup analysis based on polyp status was performed.ResultsA total of 327 patients were included in this study. Patients with a SNOT-22 score between 10 and 19 had the lowest chance of achieving an MCID (37.5%) and received a relative mean worsening of their quality of life (QoL) after ESS (+18.8%). Patients with a SNOT-22 score greater than 30 obtained a greater than 75% chance of achieving an MCID, and there was a relative improvement of 45% in QoL (all < -44.9%) after ESS. Outcomes from the polyp status subgroup analysis were similar to the findings from the overall cohort.ConclusionOutcomes from this study suggest that patients with a preoperative SNOT-22 score higher than 30 points receive a greater than 75% chance of achieving an MCID and on average obtain a 45% relative improvement in their QoL after ESS. Patients with SNOT-22 score of less than 20 did not experience improved QoL from ESS.
| S-EPMC4481170 | biostudies-literature
Project description:BackgroundOperating rooms (ORs) are one of the costliest units in a hospital, therefore the cumulative consequences of any kind of inefficiency in OR management lead to a significant loss of revenue for the hospital, staff dissatisfaction, and patient care disruption. One of the possible solutions to improving OR efficiency is knowing a reliable estimate of the duration of operations. The literature suggests that the current methods used in hospitals, e.g., a surgeon's estimate for the given surgery or taking the average of only five previous records of the same procedure, have room for improvement.MethodsWe used over 4 years of elective surgery records (n = 52,171) from one of the major metropolitan hospitals in Australia. We developed robust Machine Learning (ML) approaches to provide a more accurate prediction of operation duration, especially in the absence of surgeon's estimation. Individual patient characteristics and historic surgery information attributed to medical records were used to train predictive models. A wide range of algorithms such as Extreme Gradient Boosting (XGBoost) and Random Forest (RF) were tested for predicting operation duration.ResultsThe results show that the XGBoost model provided statistically significantly less error than other compared ML models. The XGBoost model also reduced the total absolute error by 6854 min (i.e., about 114 h) compared to the current hospital methods.ConclusionThe results indicate the potential of using ML methods for reaching a more accurate estimation of operation duration compared to current methods used in the hospital. In addition, using a set of realistic features in the ML models that are available at the point of OR scheduling enabled the potential deployment of the proposed approach.
| S-EPMC10693694 | biostudies-literature
Project description:PurposeTo develop a method for predicting postoperative anterior chamber depth (ACD) in cataract surgery patients based on preoperative biometry, demographics, and intraocular lens (IOL) power.MethodsPatients who underwent cataract surgery and had both preoperative and postoperative biometry measurements were included. Patient demographics and IOL power were collected from the Sight Outcomes Research Collaborative (SOURCE) database. A gradient-boosting decision tree model was developed to predict the postoperative ACD. The mean absolute error (MAE) and median absolute error (MedAE) were used as evaluation metrics. The performance of the proposed method was compared with five existing formulas.ResultsIn total, 847 patients were assigned randomly in a 4:1 ratio to a training/validation set (678 patients) and a testing set (169 patients). Using preoperative biometry and patient sex as predictors, the presented method achieved an MAE of 0.106 ± 0.098 (SD) on the testing set, and a MedAE of 0.082. MAE was significantly lower than that of the five existing methods (P < 0.01). When keratometry was excluded, our method attained an MAE of 0.123 ± 0.109, and a MedAE of 0.093. When IOL power was used as an additional predictor, our method achieved an MAE of 0.105 ± 0.091 and a MedAE of 0.080.ConclusionsThe presented machine learning method achieved greater accuracy than previously reported methods for the prediction of postoperative ACD.Translational relevanceIncreasing accuracy of postoperative ACD prediction with the presented algorithm has the potential to improve refractive outcomes in cataract surgery.
| S-EPMC7757635 | biostudies-literature
Project description:There is controversy about relative contributions of ictal scalp video EEG recording (vEEG), routine scalp outpatient interictal EEG (rEEG), intracranial EEG (iEEG) and MRI for predicting seizure-free outcomes after temporal lobectomy. We reviewed NIH experience to determine contributions at specific time points as well as long-term predictive value of standard pre-surgical investigations.Raw data was obtained via retrospective chart review of 151 patients. After exclusions, 118 remained (median 5 years follow-up). MRI-proven mesial temporal sclerosis (MTSr) was considered a separate category for analysis. Logistic regression estimated odds ratios at 6-months, 1-year, and 2 years; proportional hazard models estimated long-term comparisons. Subset analysis of the proportional hazard model was performed including only patients with commonly encountered situations in each of the modalities, to maximize statistical inference.Any MRI finding, MRI proven MTS, rEEG, vEEG and iEEG did not predict two-year seizure-free outcome. MTSr was predictive at six months (OR=2.894, p=0. 0466), as were MRI and MTSr at one year (OR=10.4231, p=0. 0144 and OR=3.576, p=0. 0091). Correcting for rEEG and MRI, vEEG failed to predict outcome at 6 months, 1year and 2 years. Proportional hazard analysis including all available follow-up failed to achieve significance for any modality. In the subset analysis of 83 patients with commonly encountered results, vEEG modestly predicted long-term seizure-free outcomes with a proportional hazard ratio of 1.936 (p=0.0304).In this study, presurgical tools did not provide unambiguous long-term outcome predictions. Multicenter prospective studies are needed to determine optimal presurgical epilepsy evaluation.
| S-EPMC5086266 | biostudies-other
Project description:ObjectiveThe objective of this study is to determine the factors influencing pancreatic surgery patients' perceptions of the shared decision-making process (SDM).BackgroundDecision-making in pancreatic surgery is complicated by the risk of morbidity and mortality and risk of early recurrence of disease. Improvement in SDM has the potential to improve the receipt of goal- and value-concordant care.MethodsThis cross-sectional survey included patients who underwent pancreatic surgery. The following components were studied in relation to SDM: modified satisfaction with decision scale (SWD), modified decisional regret scale (DRS), quality of physician and patient interaction, and the impact of quality of life (FACT-Hep). Correlations were computed using Pearson's correlation score and a regression model.ResultsThe survey completion rate was 72.2% (of 40/55) and the majority (72.5%) of patients underwent pancreaticoduodenectomy. There were significant positive relationships between the SDM measure and (DRS, SWD; r = 0.70, P < 0.001) and responses to questions regarding how well the patient's actual recovery matched their expectations before treatment (r = 0.62, P < 0.001). The quality of the physician-patient relationship correlated with how well recovery matched expectations (r = 0.53, P = 0.002). SDM measure scores were significant predictors of the decision evaluation measure (R2(adj) = 0.48, P < 0.001), FACT-Hep (R2(adj) = 0.15, P < 0.001), and recovery expectations measure (R2(adj) = 0.37, P < 0.001).ConclusionsImproved SDM in pancreatic surgery is associated with more realistic recovery expectations, decreased decisional regret, and improved quality of life.
| S-EPMC10431427 | biostudies-literature
Project description:It is well known that patients who suffer from peripheral (noncardiac) vascular disease often have coexisting atherosclerotic diseases of the heart. This may leave the patients susceptible to major adverse cardiac events, including death, myocardial infarction, unstable angina, and pulmonary edema, during the perioperative time period, in addition to the many other complications they may sustain as they undergo vascular surgery procedures, regardless of whether the procedure is performed as an open or endovascular modality. As these patients are at particularly high risk, up to 16% in published studies, for postoperative cardiac complications, many proposals and algorithms for perioperative optimization have been suggested and studied in the literature. Moreover, in patients with recent coronary stents, the risk of non-cardiac surgery on adverse cardiac events is incremental in the first 6 months following stent implantation. Just as postoperative management of patients is vital to the outcome of a patient, preoperative assessment and optimization may reduce, and possibly completely alleviate, the risks of major postoperative complications, as well as assist in the decision-making process regarding the appropriate surgical and anesthetic management. This review article addresses several tools and therapies that treating physicians may employ to medically optimize a patient before they undergo noncardiac vascular surgery.
| S-EPMC4492637 | biostudies-literature
Project description:IntroductionThis paper presents the preliminary results of a decision-tree analysis of Patient Decision Aids (PDA). PDAs are online or offline tools used to structure health information, elicit relevant values and emphasize the decision as a process, in ways that help patients make more informed health decisions individually or with relevant others.MethodTwenty PDAs are randomly selected from the International Patient Decision Aids Standards (IPDAS) ( https://decisionaid.ohri.ca/AZlist.html ) approved list. An evaluation tool is built bottom-up and top-down and results are described in terms of communicating uncertainty, completeness of the decision tree, ambiguous or misleading phrasing, overall strategies suggested within personal stories.ResultsTwelve of the analyzed PDAs had branches of the decision tree which were not discussed in the tool and 6 had logically ambiguous phrasing. Many tools included dichotomous options, when the option range was wider. Several options were clustered within the "Do not take/Do not do" option and thus the PDA failed to provide all comparisons necessary to make a decision. Some tools employ expressions that do not differentiate between lack of information and known negative effects. Other tools provide unequal amounts or non-comparable bits of information about the options.ConclusionThese results indicate a very loose range of interpretations of what constitutes an option, a treatment, and a treatment option. It thus emphasizes a gap between theory and practice in the evaluation of PDAs. Future developments of PDA evaluation tools should keep track of missing decision tree branches, accurate communication of uncertainty, ambiguity, and lack of knowledge and consider using measures for evaluating the completeness of the option spectrum at an agreed period in time.
| S-EPMC6642566 | biostudies-literature
Project description:In this modern era of technological advancements, though many centers are contemplating complex surgical procedures on the pancreas, morbidity is still high and around 30-35 %. Post-operative bleeding complications are the most worrisome of all, which need vigilance by the operating team. Early recognition and prompt management using endoscopy, intervention radiology or urgent surgery, with a low threshold for relaparotomy is needed to avoid mortality. After successfully completing more than 500 Whipple's operations and over 300 Frey's procedures in the last 10 years, our bleeding complication, which is around 2 %, has substantially increased. This increase over the last couple of years is seen with usage of harmonic scalpel in pancreatic surgery. Here we report our recent encounter with bleeding in the post-operative period after Whipple's pancreaticoduodenectomy and Frey's procedure, where harmonic scalpel was used. We have recommended our suggestion to avoid this complication, by adopting a simple technique. We have achieved optimal results by applying this technique in our subsequent cases.
| S-EPMC3693348 | biostudies-other
Project description:BackgroundAppropriate blood component transfusion might differ between intraoperative massive bleeding and traumatic massive bleeding in the emergency department because trauma patients initially bleed undiluted blood and replacement typically lags behind blood loss. We compared these two blood loss scenarios, intraoperative and traumatic, using a computer simulation.MethodsWe modified the multi-compartment dynamic model developed by Hirshberg and implemented it using STELLA 9.0. In this model, blood pressure changes as blood volume fluctuates as bleeding rate and transcapillary refill rate are controlled by blood pressure. Using this simulation, we compared the intraoperative bleeding scenario with the traumatic bleeding scenario. In both scenarios, patients started to bleed at a rate of 50 ml/min. In the intraoperative bleeding scenario, fluid was administered to maintain isovolemic status; however, in the traumatic bleeding scenario, no fluid was supplied for up to 30 min and no blood was supplied for up to 50 min. Each unit of packed red blood cells (PRBC) was given when the hematocrit decreased to 27%, fresh frozen plasma (FFP) was transfused when plasma was diluted to 30%, and platelet concentrate (PC) was transfused when platelet count became 50,000/ml.ResultsIn both scenarios, the appropriate ratio of PRBC:FFP was 1:0.47 before PC transfusion, and the ratio of PRBC:FFP:platelets was 1:0.35:0.39 after initiation of PC transfusion.ConclusionThe ratio of transfused blood component did not differ between the intraoperative bleeding and traumatic bleeding scenarios.
| S-EPMC7724118 | biostudies-literature
Project description:BACKGROUND:There is limited consensus regarding risk factors for postoperative bleeding. The objective of this work was to investigate the capability of machine learning techniques in combination with practice-based longitudinal electronic medical record data for identifying potential new risk factors for postoperative bleeding and predicting patients at high risk of postoperative bleeding. METHODS:A retrospective study was conducted for patients who underwent colorectal surgery 1998-2015 at a single tertiary referral center. Various predictors were extracted from electronic medical record. The outcome of interest was the occurrence of postoperative bleeding within 7 days of surgery. Logistic regression and gradient boosting machine models were trained. Area under the receiver operating curve and area under the precision recall curve were used to evaluate the performance to different models. RESULTS:Of 13,399 cases undergoing colorectal resection, 1,680 (12.5%) experienced postoperative bleeding. A total of 299 variables were evaluated. Logistic regression and gradient boosting machine models returned an area under the receiver operating curve of 0.735 and 0.822 and area under the precision recall curve of 0.287 and 0.423, respectively. In addition to well-known risk factors for postoperative bleeding, nutrition (ranked third), weakness (ranked fifth), patient mobility (ranked sixth), and activity level (ranked eighth) were found to be novel predictors in the gradient boosting machine model based on permutation importance. CONCLUSION:The study identified measures of functional capacity of patient as novel predictors of postoperative bleeding. The study found that risk of postoperative bleeding can be assessed, allowing for better use of human resources in addressing this important adverse event after surgery.
| S-EPMC6263850 | biostudies-literature