Explainable Model Using Shapley Additive Explanations Approach on Wound Infection after Wide Soft Tissue Sarcoma Resection: "Big Data" Analysis Based on Health Insurance Review and Assessment Service Hub

Background and Objectives: Soft tissue sarcomas represent a heterogeneous group of malignant mesenchymal tissues. Despite their low prevalence, soft tissue sarcomas present clinical challenges for orthopedic surgeons owing to their aggressive nature, and perioperative wound infections. However, the low prevalence of soft tissue sarcomas has hindered the availability of large-scale studies. This study aimed to analyze wound infections after wide resection in patients with soft tissue sarcomas by employing big data analytics from the Hub of the Health Insurance Review and Assessment Service (HIRA). Materials and Methods: Patients who underwent wide excision of soft tissue sarcomas between 2010 and 2021 were included. Data were collected from the HIRA database of approximately 50 million individuals' information in the Republic of Korea. The data collected included demographic information, diagnoses, prescribed medications, and surgical procedures. Random forest has been used to analyze the major associated determinants. A total of 10,906 observations with complete data were divided into training and validation sets in an 80:20 ratio (8773 vs. 2193 cases). Random forest permutation importance was employed to identify the major predictors of infection and Shapley Additive Explanations (SHAP) values were derived to analyze the directions of associations with predictors. Results: A total of 10,969 patients who underwent wide excision of soft tissue sarcomas were included. Among the study population, 886 (8.08%) patients had post-operative infections requiring surgery. The overall transfusion rate for wide excision was 20.67% (2267 patients). Risk factors among the comorbidities of each patient with wound infection were analyzed and dependence plots of individual features were visualized. The transfusion dependence plot reveals a distinctive pattern, with SHAP values displaying a negative trend for individuals without blood transfusions and a positive trend for those who received blood transfusions, emphasizing the substantial impact of blood transfusions on the likelihood of wound infection. Conclusions: Using the machine learning random forest model and the SHAP values, the perioperative transfusion, male sex, old age, and low SES were important features of wound infection in soft-tissue sarcoma patients.

Timing of Blood Transfusions and 30-Day Patient Outcomes After Coronary Artery Bypass Graft Surgery

OBJECTIVE

Packed red blood cell transfusion during coronary artery bypass graft surgery is known to be associated with adverse outcomes. However, the association of the timing between transfusions in relation to discharge and 30-day postoperative outcomes has not been studied. The study authors investigated the impact of transfusion timing on 30-day surgical outcomes.

DESIGN

A retrospective review.

SETTING

At a single tertiary-care academic hospital.

PARTICIPANTS

A total of 2,481 adult patients underwent primary coronary artery bypass graft surgery between January 2014 and December 2020.

MEASUREMENTS AND MAIN RESULTS

The relationship between the timing of packed red blood cell transfusion (intraoperative, postoperative, or both) and 30-day postoperative outcome variables was calculated as an odds ratio. The influence of timing of transfusion on adjusted probability of postoperative complications was plotted against the lowest intraoperative hematocrit. The median age of the population was 67 years (60.0-74.0), body mass index was 28.5 (25.6-32.3) kg/m², and 497 (20.0%) were female. A total of 1,588 (36%) patients received packed red blood cell transfusions; 182 (7.3%) received intraoperative transfusions, 489 (19.7%) received postoperative transfusions, and 222 (9.0%) received both (intraoperative and postoperative transfusions). Postoperative transfusion was associated with significantly higher odds of readmission (1.83 [1.32-2.54], p = 0.002) and heart failure (1.64 [1.2-2.23], p = 0.008) compared to patients with no transfusions; whereas intraoperative transfusions were not.

CONCLUSION

The authors' data suggested that the postoperative timing of transfusion in patients undergoing coronary artery bypass graft surgery may be associated with an increased incidence of 30-day heart failure and readmission. Prospective research is needed to conclusively confirm these findings.

Effect of Perioperative Blood Transfusions and Infectious Complications on Inflammatory Activation and Long-Term Survival Following Gastric Cancer Resection

Background: The aim of this study was to evaluate the impact of perioperative blood transfusion and infectious complications on postoperative changes of inflammatory markers, as well as on disease-free survival (DFS) in patients undergoing curative gastric cancer resection. Methods: Multicenter cohort study in all patients undergoing gastric cancer resection with curative intent. Patients were classified into four groups based on their perioperative course: one, no blood transfusion and no infectious complication; two, blood transfusion; three, infectious complication; four, both transfusion and infectious complication. Neutrophil-to-lymphocyte ratio (NLR) was determined at diagnosis, immediately before surgery, and 10 days after surgery. A multivariate Cox regression model was used to analyze the relationship of perioperative group and dynamic changes of NLR with disease-free survival. Results: 282 patients were included, 181 in group one, 23 in group two, 55 in group three, and 23 in group four. Postoperative NLR changes showed progressive increase in the four groups. Univariate analysis showed that NLR change > 2.6 had a significant association with DFS (HR 1.55; 95% CI 1.06−2.26; p = 0.025), which was maintained in multivariate analysis (HR 1.67; 95% CI 1.14−2.46; p = 0.009). Perioperative classification was an independent predictor of DFS, with a progressive difference from group one: group two, HR 0.80 (95% CI: 0.40−1.61; p = 0.540); group three, HR 1.42 (95% CI: 0.88−2.30; p = 0.148), group four, HR 2.85 (95% CI: 1.64−4.95; p = 0.046). Conclusions: Combination of perioperative blood transfusion and infectious complications following gastric cancer surgery was related to greater NLR increase and poorer DFS. These findings suggest that perioperative blood transfusion and infectious complications may have a synergic effect creating a pro-inflammatory activation that favors tumor recurrence.

Association of preoperative anemia and increased risk of blood transfusion and length of hospital stay in adults undergoing hip and knee arthroplasty: An observational study in a single tertiary center

BACKGROUND AND AIMS

Anemia is a common feature in patients presenting for major elective surgery, and it is considered an independent risk factor associated with adverse outcomes. Although several studies suggest that preoperative anemia is associated with poor outcomes after elective orthopedic surgery, data are still scarce in middle- and low-income countries where this problem may be even greater. The objective of this study was to evaluate the impact of preoperative anemia in clinical outcomes in patients submitted to hip and knee arthroplasty in a single tertiary hospital.

METHODS

Medical records of 234 adult patients submitted to knee and hip arthroplasty from January 2018 to July 2020 were retrospectively reviewed. Patient's demographics (ie, age and gender), pre- and postoperative hemoglobin level (Hb), allogeneic red blood cell (RBC) transfusion, intensive care admission, length of hospital stay, hospital readmissions, and mortality up to 30 days after the surgery were analyzed. Outcomes were evaluated according to preoperative anemia status based on World Health Organization (WHO) criteria.

RESULTS

Mean age was 70 years with a slight female predominance (57.6%). The prevalence of anemia was 30.7% (72/234) being more prevalent in female (33.3% vs 26.7%). Preoperative anemia was significantly associated with greater rate of blood transfusion (34.5% vs 5.6%; P = .001), prolonged length of hospital stay (6.48 days vs 3.36 days; P = .001), and higher rate of intensive care unit admission (47.2% and 29.6% P = .009). Preoperative anemia had no effect on 30-day readmission and mortality for both males and females.

CONCLUSIONS

Our retrospective study demonstrated that preoperative anemia is a common problem among orthopedic patients and is associated with increased transfusion risk and worse outcomes. Strategies to identify and treat anemic patients before elective surgery are critical to improving clinical outcomes.

Perioperative blood transfusions and survival in resected pancreatic adenocarcinoma patients given multimodality therapy

BACKGROUND AND OBJECTIVES

The impact of perioperative blood transfusion (PBT) on outcomes for pancreatic ductal adenocarcinoma (PDAC) patients given multimodality therapy (MMT) remains undefined. We sought to evaluate the association of PBT with survival after PDAC resection.

METHODS

Pancreatectomy patients (July 2011-December 2017) who received MMT were abstracted from a prospective database. Overall survival (OS) was compared by PBT within 30 days, 24 h (24HR-BT), or 24 h until 30 days (Postop-BT).

RESULTS

Most (76.6%) of 312 MMT patients underwent neoadjuvant therapy (NT). Eighty-nine patients (28.5%) received PBT; 58 (18.6%) 24HR-BT, and 31 (9.9%) Postop-BT. Compared with surgery-first, NT patients received more 24HR-BTs (22.2% vs. 6.8%, p = 0.003) and PBTs overall (32.6% vs. 15.1%, p = 0.004). Overall median OS was 45 months. The association of PBT with shorter median OS appeared limited to first 24-h transfusions (34 months 24HR-BT vs. 48 months Postop-BT vs. 53 months no-PBT, p = 0.009) and was dose-dependent, with a median OS of 52 months for 0 units 24HR-BT, 35 months for 1 unit, and 25 months for ≥2 units (p = 0.004). Independent predictors of OS included node-positivity (hazard ratio [HR]: 1.93, p < 0.001), perineural invasion (HR: 1.64, p = 0.050), postoperative pancreatic fistula (HR: 1.94, p = 0.018), and 24HR-BT (HR: 1.75, p = 0.001).

CONCLUSIONS

Transfusions given within 24 h are associated with dose-dependent decreases in survival after pancreatectomy for PDAC.

Risk factors of perioperative complications and transfusion following total hip arthroplasty in systemic lupus erythematosus patients

BACKGROUND

In recent years, hip arthroplasty rates in systemic lupus erythematosus (SLE) patients have been increasing rapidly. Although patients with SLE generally show beneficial or desirable functional outcomes following total hip arthroplasty (THA), it has been reported that SLE patients after THA have increased risk of postoperative complications, especially during the period of hospitalization.

OBJECTIVES

In the present study, we aimed to identify possible factors associated with complications or transfusion of THA in SLE patients during hospitalization.

METHODS

The present study was a retrospective study conducted in Peking Union Medical College Hospital. Data were collected from medical records of patients who underwent THA from January 2012 to June 2018. The primary outcome variable was perioperative complications, which was defined as having one or more of the following conditions: high fever, infection, impaired wound healing, venous thrombosis of the lower extremities, hematoma, arrhythmia, implant complications. The secondary outcome was perioperative transfusion.

RESULTS

During January 2012 to June 2018, 100 patients had taken the surgery of THA. After multivariate analysis, independent risk factors for perioperative complications were: age ≥ 45 years (p = 0.001), SLE with other connective tissue diseases (p = 0.029), high temperature (p = 0.030), positive anti-dsDNA antibody (p = 0.043), and Systemic Lupus International Collaborative Clinics/American College of Rheumatology (SLICC/ACR) Damage Index ≥ 3 (p = 0.008). Independent risk factors for perioperative transfusion were bilateral THA (p = 0.029), low hemoglobin (p = 0.021) and abnormal renal function (p = 0.021).

CONCLUSION

For SLE patients following THA, age > 45 years, SLE with other connective tissue disease, high temperature, positive anti-dsDNA antibody and SLICC/ACR Damage Index ≥ 3 were the risk factors of complications during hospitalization and bilateral THA, low hemoglobin and abnormal renal function were the risk factors of transfusion.