Development of an Integrated Nomogram for Predicting Postoperative Deep Vein Thrombosis Risk in Trauma Patients: Combining Thrombosis Risk Assessment Profile Score and Thrombosis Biomarkers.

The incidence of deep vein thrombosis (DVT) after traumatic fracture is high, and DVT causes serious adverse effects on the postoperative recovery of patients. The purpose of this study was to explore the effect of coagulation-related indicators combined with vascular ultrasound measurements for the risk assessment of DVT after secondary traumatic fracture, and to provide a new method for predicting the occurrence of DVT. The clinical data of patients with secondary traumatic fracture surgery in our hospital from January 2019 to January 2022 were retrospectively analyzed. The patients were divided into a non-DVT group and a DVT group according to whether DVT was indicated in the medical record system. The coagulation-related indices and vascular ultrasound measurements of the two groups were compared, and the risk factors for postoperative DVT were analyzed by bivariate correlation and multivariate logistic regression. According to the medical record system, 55 patients (47.41%) had DVT, and 61 patients (52.59%) did not have DVT. There was no significant difference in prothrombin time (PT) or activated partial thromboplastin time (APTT) between the two groups (p > 0.05). The thrombin time (TT) in the DVT group was lower than that in the non-DVT group. The levels of fibrinogen (FIB) and D-dimer (D-D) in the DVT group were higher than those in the non-DVT group (t = 2.766, 3.242, 2.649, p = 0.007, 0.002, 0.009). Spearman correlation analysis showed that peak systolic velocity (Vs), end-diastolic velocity (Vd), pulsatility index (PI), resistance index (RI), FIB, and D-D were positively correlated with the risk of DVT after secondary traumatic fracture surgery (r = 0.264, 0.656, 0.293, 0.276, 0.287, 0.251, p < 0.05). TT was negatively correlated with DVT risk after secondary traumatic fracture surgery (r = -0.249, p < 0.05). The measurements of peak systolic velocity (Vs), end diastolic velocity (Vd), pulsatility index (PI) and resistance index (RI) in the DVT group were higher than those in the non-DVT group (t = 2.663, 2.998, 3.135, 2.953, p = 0.009, 0.003, 0.002, 0.004). FIB, D-D, Vs, Vd, PI, and RI were independent risk factors for DVT after secondary traumatic fracture surgery (Odds Ratio (OR) = 1.483, 2.026, 2.208, 1.893, 1.820, 1.644, p < 0.05). TT index was an independent protective factor for DVT after secondary traumatic fracture surgery (OR = 0.868, p < 0.05). The sensitivity and specificity for prediction of DVT based on combined coagulation-related indicators and vascular ultrasound imaging measurements were higher than those of individual measurements (p < 0.05). Coagulation-related indicators and vascular ultrasound parameters can effectively predict the formation of DVT. Through the analysis of factors related to DVT formation, screening of high-risk patients for effective intervention may help to reduce the risk of DVT. Further verification in additional, large-scale clinical trials is advocated.

The goal was to investigate the relationship between serum vascular endothelial growth factor (VEGF), P-selectin, high-density lipoprotein cholesterol (HDL-C), platelet parameters, and coagulation function indexes and postoperative deep vein thrombosis (DVT) in patients with traumatic fracture. A total of 150 patients with traumatic fractures after DVT were selected as the DVT group, and 150 patients with traumatic fractures without DVT during the same period were selected as the non-DVT group. Serum VEGF, P-selectin, HDL-C, platelet parameters including platelet count (PLT), mean platelet volume (MPV), platelet distribution width (PDW), plateletcrit (PCT), platelet large cell ratio (P-LCR), and plasma coagulation function indexes including thrombin time (TT), prothrombin time (PT), activated partial thrombin time (APTT), fibrinogen (FIB), and D-dimer (D-D) were measured. Pearson's correlation was performed to analyze the correlation between serum VEGF, P-selectin, and coagulation function indexes, and binary logistic regression was used to analyze the risk factors of DVT. Serum VEGF and P-selectin in the DVT group were higher while HDL-C was lower than those in the non-DVT group (p < 0.05). Serum VEGF and P-selectin were negatively correlated with plasma D-D and FIB (p < 0.05), and serum HDL-C was negatively correlated (p < 0.05). Compared with the non-DVT group, MPV, PDW, and P-LCR in the DVT group were decreased (p < 0.05). Multivariate logistic regression analysis showed that P-LCR was a risk factor for postoperative DVT in patients with traumatic fractures (p < 0.05). Serum VEGF and P-selectin are higher and HDL-C is lower in patients with DVT after postoperative traumatic fracture than in patients without DVT. Combined detection of serum VEGF, P-selectin, HDL-C, and coagulation function indexes may help to reduce the risk of DVT. Platelet parameters (MPV, PDW, P-LCR) have certain reference values for the clinical diagnosis and disease evaluation of DVT.

New-onset deep vein thrombosis (DVT) reportedly affects prognosis and surgical outcomes of elderly patients. However, its effect on distal femur fractures (DFFs) remains unclear. We aimed to address the epidemiological characteristics and the associated predictors for post-operative DVT in patients with closed DFFs over age 60 years old. We designed a prospective cohort trial at our hospital between October 2018 and June 2020 and recruited consecutive 140 patients over age 60 years diagnosed with closed DFFs. We examined location and prognosis of postoperative DVT and then conducted a three month follow-up. We used Duplex ultrasonography (DUS) to diagnose DVT in all patients and then classified the subjects into DVT and non-DVT groups. We further classified DVTs into proximal, distal, and mixed thromboses and then performed Whitney U test or t test, receiver operating characteristic (ROC) curve analysis, Chi-square test, and multiple logistic regression analysis to confirm the adjusted factors of post-operative DVT. We found a 35% (n = 49) overall incidence of post-operative DVTs, which occurred 5.7 days following open reduction internal fixation (ORIF). Among patients with post-operative DVTs, 53.1% (n = 26) and 10.2% (n = 5) were distal and proximal thromboses, respectively. Additionally, peroneal veins were the most common DVT sites (71.4%, n = 35). Multivariate analysis revealed that venous thrombosis at admission (odds ratio [OR], 4.619; 95% confidence interval [CI]: 2.072-10.299; P = 0.000), operation duration over 195 minutes (OR, 3.289; 95% CI, 1.155-9.370; P = 0.026), intra-operative blood loss over 325 mL (OR, 2.538; 95% CI, 1.047-6.155; P = 0.039) were the three independent risk factors of post-operative DVT. Unified antithrombotic agents after diagnosis showed that 16.3% (n = 8) of DVTs were completely recanalized, 12.6 days after first diagnosis. Our findings indicate a strong association between venous thrombosis at admission, the longer operation duration, and considerable intra-operative blood loss with high risk of post-operative DVTs in patients over age 60 years with closed DFFs. Preventive approaches for postoperative DVTs should seek to shorten operation duration and reduce intra-operative blood loss.

PurposeThere is a significant risk of DVT after TKA. We aim to evaluate the potential risk factors for postoperative DVT in the lower extremities in TKA patients over 60 years of age and provide a reference for the effective prevention of DVT.MethodsThis retrospective study included patients older than 60 who underwent TKA surgery in our hospital from May 2015 to May 2022 and compared and analyzed patients' personal characteristics and clinical data with or without postoperative DVT. Logistic regression analysis was performed to determine the potential risk factors for DVT after TKA. The sensitivity and specificity of each risk factor in the diagnosis of DVT were compared by the ROC curve, and the value of this model in the diagnosis of DVT was further investigated using a multivariable combined diagnosis ROC curve model.ResultsA total of 661 patients over 60 who underwent TKA were included. Preoperative Hematocrit (HCT), platelet count, anesthesia mode, postoperative D-dimer, ESR, diabetes mellitus, and other aspects of the DVT group and non-DVT group were statistically significant after TKA (P < 0.05). Multivariate logistics regression analysis showed that preoperative HCT, anesthesia mode, and diabetes were independent risk factors for DVT in patients over 60 years old after TKA. Compared with the univariate ROC model, the multivariable combined ROC curve analysis model has a higher diagnostic value for the diagnosis of DVT.ConclusionDVT is common in patients over 60 years of age after TKA, and there is a multivariable influence on its pathogenesis. For patients over 60 with diabetes, neuraxial anesthesia is recommended for patients with high preoperative HCT levels, which may reduce the incidence of postoperative DVT.

This study aims to elucidate the risk factors associated with postoperative lower extremity deep vein thrombosis (DVT) in patients afflicted with gynecologic malignancies. A comprehensive search was conducted across CNKI, CQVIP, Wanfang, and PubMed databases for literature published from January 1, 2024, concerning the risk factors for postoperative DVT in patients with gynecologic cancers. Two researchers independently and objectively screened, extracted, and evaluated the pertinent data. Subsequently, the extracted data were subjected to meta-analysis using STATA software. A total of twelve studies fulfilling the inclusion criteria were analyzed, encompassing 2,553 cases. The meta-analysis revealed that significant risk factors for postoperative lower extremity DVT in patients with gynecologic malignancies include age [Odds Ratio (OR) = 1.35, 95% Confidence Interval (CI) (1.19, 1.54), P < 0.001], Body Mass Index (BMI) [OR = 1.67, 95% CI (1.05, 2.66), P < 0.001], plasma D-dimer levels [OR = 3.39, 95% CI (1.24, 9.24), P < 0.001], duration of surgery [OR = 2.24, 95% CI (1.24, 4.01), P < 0.001], and duration of postoperative bed rest [OR = 2.14, 95% CI (1.56, 2.94), P < 0.001]. The study identifies multiple risk factors influencing the incidence of postoperative lower extremity DVT in patients with gynecologic malignancies. Notably, age, BMI, plasma D-dimer levels, surgical duration, and postoperative bed rest emerge as significant predictors. These findings underscore the necessity for targeted prophylaxis and therapeutic interventions in the clinical management of such patients.

Background: Deep vein thrombosis (DVT) is a serious complication in stroke patients and may lead to the devastating consequences of a pulmonary embolism. The risk factors for DVT in acute stroke are advanced age, high National Institute of Health Stroke Scale (NIHSS) score, hemiparesis, immobility, female gender, atrial fibrillation. The present study is aimed at identifying the prevalence and risk factors for DVT in acute stroke patients. Methods: This was a prospective cross sectional study conducted in of Dhaka Medical College and Hospital from January 2022 to December 2023. Data was collected in a preformed questionnaire. Statistical analysis was performed using IBM SPSS version 26.0. Continuous variables were analyzed in the form of the means with standard deviations (Mean ± SD). Categorical variables were shown as numbers and proportions. Continuous data were analyzed using the independent samples t-test. Categorical data were analyzed using the chi-squared test. Univariate variables with a p-value of &lt;0.05 were retained in a binary logistic regression model. Receiver operating characteristic (ROC) curve analysis was performed by identifying the area under the ROC curve (AUC) to evaluate the performance of the logistic regression model. Statistical significance was defined as a p-value of &lt; 0.05. Results: A total of 106 patients with acute stroke (AS) were included in the study. The included patients were divided into two groups: DVT and non-DVT group. Out of 106 patients, 34(32.07%) patients presented with DVT. Patients with DVT were older than those without DVT (62.7 ± 10.7 vs. 56.5 ± 11.9 years, p &lt; 0.05). Females were more affected by DVT (58.88% vs. 26.85%, p&lt;0.05). In the DVT group, the level of D-dimer was significantly higher than that in the non- DVT group (2.2 ± 1.7 vs. 0.45 ± 1.1, p &lt; 0.05). Elevated CRP and low serum albumin level were also observed in DVT group which was statistically significant. (p&lt;0.05). Multiple logistic regression analysis showed that age&gt;60years, NIHSS score&gt;25 and a D-dimer level of ≥ 1.52 μg/mL and caprine score &gt;6 were independent factors for the presence of DVT at the time of stroke admission. Odds ratio for age, Caprini RAM score, NIHSS score and elevated d-dimer were 1.043(1.000–1.075, p=0.029),1.43(0.85-0.1.96, p=0.001),1.266(1.168-1.284, p=0.008) and1.446 (1.130–1.849, p=0.003) respectively. Conclusion: The present study has showed that advanced age, high NIHSS and caprini score and raised serum D-dimer levels are independent predictors of DVT in stroke patients. A further large multicenter study should be done to provide a better management to the patients of DVT in stroke patients.

Objective To investigate the effectiveness of the nursing intervention on deep vein thrombosis (DVT) predicting after gynecologic laparoscopic surgery based on the risk assessment nomogram. Methods From July 2015 to July 2017, the clinical data of 431 patients undergoing gynecologic laparoscopic surgery at Shengjing Hospital of China Medical University were collected. The independent risk factors affecting postoperative DVT were analyzed. The R software was used to establish a nomogram model of DVT risks after gynecologic laparoscopic surgery. A prospective enrollment of 100 patients undergoing gynecologic laparoscopic surgery was randomly divided into a study group of 50 patients and a control group of 50 patients by random number table. The control group received routine care after surgery. The study group implemented a care plan based on the DVT risk nomogram model beyond what was given the the control group. The plasma D-dimer levels and the incidence of DVT on the 3rd and 5th day after surgery were compared between the two groups before and after the intervention. Results The incidence of postoperative DVT in the 431 patients underwent laparoscopic surgery was 10.4% (45/143). Logistic regression analysis showed that age, D-dimer ≥0.5 mg/L, head position during operation, blood loss≥400 ml, operation time≥ 1 h, bed time> 5 d were independent risk factors of postoperative DVT. The nomogram model predicted a C-index of 0.857 for the risk of DVT after gynecologic laparoscopic surgery, and the discrimination was good. After the nursing intervention based on the nomogram, the plasma D-dimer level of the study group was (0.47±0.09) and (0.54±0.17) mg/L on the 3rd and 5th day after the operation, respectively, which were lower than the control group. The difference was statistically significant (P<0.05) . On the 5th day after surgery, the incidence of DVT in the study group was 2.0% (1/50) , and that in the control group was 14.0% (7/50) . The difference was statistically significant (P<0.05) . Conclusions Nursing interventions based on the nomogram model can reduce the incidence of DVT after gynecologic laparoscopic surgery. Key words: Venous thrombosis; Gynecologic diseases; Laparoscopic surgery; Nomogram model; Nursing intervention

Background and aimThe study of prevalence and risk factors of postoperative lower limb deep vein thrombosis (DVT) in Thai gynecologic patients was limited. The present study was conducted to evaluate this issue.MethodsThe patients were age > 15 years old without a history of DVT or pulmonary emboli (PE) scheduled for laparotomy or vaginal gynecologic surgery between May and November 2020 were invited to participate. All of these patients were scheduled for a complete duplex ultrasound to detect lower limb DVT 72 h before and within 14 days after the operation. The patients without DVT were scheduled for an interview by telephone about DVT symptoms 30 days after the operation. The clinical variables were compared using univariate and multivariate analysis to identify the independent factors related to the development of DVT.ResultsOne hundred and twelve patients met the inclusion criteria. Of these patients, 44 cases (39.3%) were diagnosed as malignancy and 102 patients underwent a hysterectomy. Post-operative DVTs were detected in six patients (5.4%) and all except one had a malignancy. Thus, the prevalence of DVT in malignancy cases was five in 44 patients (11.4%). The independent risk factors for postoperative DVT were age > 60-year-old and receiving a perioperative blood transfusion. Five of six DVT patients received low molecular-weight heparin for treatment of DVT and none developed PE. The rest of the participants reported no symptom-related DVTs from the interview 30 days after the operation.ConclusionThe prevalence of postoperative DVT in gynecologic patients was 5%, and the independent risk factors were elderly patients and receiving a perioperative blood transfusion.

To develop predictive models for assessing deep vein thrombosis (DVT) risk among lumbar disc herniation (LDH) patients and evaluate their performances. A retrospective study was conducted on 798 LDH patients treated at the First Hospital of Hebei Medical University from January 2017 to December 2023. The patients were divided into a training set (n = 558) and a test set (n = 240) using computer-generated random numbers in a ratio of 7:3. Patients without DVT in the training set were categorized as the non-DVT group (n = 463), while those diagnosed with DVT were the DVT group (n = 95). Univariate analysis was performed to compare clinical data between the two groups. Data with statistical significance were used for the development of a Logistic regression model, Gradient boosting model, and Random Forest model. Model performance was evaluated through receiver operating characteristic (ROC) curve analysis and calibration curve assessment. In the training set, univariate analysis revealed significant differences in age, platelets (PLT), cholesterol (TC), triglycerides (TG), glycated hemoglobin (HbAlc), D-dimer (D-D), fibrinogen (FIB), activated partial thromboplastin time (APTT), prothrombin time (PT), and thrombin time (TT) between the non-DVT group and the DVT group (all P<0.05). Predictive models were constructed based on these indicators. The areas under the ROC curves (AUCs) in the training set were as follows (in descending order): Random Forest model (0.978) > Gradient boosting model (0.943) > Logistic regression model (0.919). In the test set, the AUCs were: Random Forest model (0.952) > Gradient boosting model (0.941) > Logistic regression model (0.908). The DeLong test indicated that the AUC of the Random Forest model in the training set was significantly higher than that of the Logistic regression model (P<0.05); however, no significant difference was observed between the other two models. Calibration curves demonstrated that the predictive probabilities from all three models closely aligned with actual DVT incidence in both sets. The Logistic regression model, Gradient boosting model, and Random Forest model constructed in this study exhibit good predictive value for the occurrence of DVT in LDH patients, aiding in the optimization of clinical management of clinical management. Among them, the Random Forest model performed the best of the three.

ObjectiveTo investigate the risk factors for deep vein thrombosis (DVT) following total hip arthroplasty (THA).MethodsPatients who underwent THA in the Department of Joint Surgery at the Sixth Affiliated Hospital of Xinjiang Medical University from September 2020 to December 2022 were retrospectively selected based on inclusion criteria. They were divided into the DVT group (n = 65) and the non-DVT group (n = 397) according to the occurrence of postoperative DVT. The following variables were reviewed for both groups: age, sex, Body Mass Index (BMI), affected limb, previous history (smoking and drinking), diabetes, hypertension, operation time, total cholesterol, triglycerides, fibrinogen, hemoglobin, albumin, platelets, D-dimer, International Normalized Ratio (INR), and fibrin degradation products. Univariate analysis was conducted on these factors, and those with statistical significance were further analyzed using a binary logistic regression model to assess their correlation with DVT after THA.ResultsA total of 462 patients were included in the study, with the DVT group representing approximately 14% and the non-DVT group approximately 86%. The DVT group had an average age of 67.27 ± 4.10 years, while the non-DVT group had an average age of 66.72 ± 8.69 years. Univariate analysis revealed significant differences in diabetes mellitus, preoperative fibrinogen, preoperative D-dimer, preoperative INR, and preoperative and postoperative fibrin degradation products between the DVT and non-DVT groups. Binary logistic regression analysis identified diabetes mellitus, elevated preoperative fibrinogen, preoperative D-dimer, and preoperative INR (p < 0.05) as risk factors for DVT after THA.ConclusionThis study found that diabetes mellitus, elevated preoperative fibrinogen, preoperative D-dimer, and preoperative INR are independent risk factors for DVT following THA. Surgeons should thoroughly assess these risk factors, implement timely and effective interventions, and guide patients to engage in functional exercises as early as possible to reduce the incidence of DVT, thereby improving the outcomes of THA and improving patient quality of life.

To explore the applicability of the Caprini Risk Assessment Scale in burn patients for evaluating the risk of deep vein thrombosis (DVT). A retrospective case-control study was conducted involving 278 burn patients from March 2021 to March 2023, with an additional independent test set of 119 patients for external validation. Patients were stratified into DVT and non-DVT groups based on the DVT incidence within one month after burn. The Caprini Risk Assessment Scale was employed to calculate scores and determine risk factors. Multivariate logistic regression analyses identified significant risk factors, and receiver operating characteristic (ROC) curves evaluated the model's predictive power. The mean Caprini score was significantly higher in the DVT group (6.61 ± 2.64) compared to the non-DVT group (4.89 ± 2.36; P < 0.001). Key risk factors included older age, increased body mass index (BMI), and a personal or family history of thrombosis. DVT patients were more prone to higher Caprini scores and classified as 'very high risk'. Logistic regression demonstrated a positive correlation between Caprini scores, risk stratification, and DVT incidence (β = 0.284, OR = 1.329; β = 0.466, OR = 1.594, respectively). The predictive model displayed strong discriminatory power, with an area under the curve (AUC) of 0.853 in the training set and 0.937 in the test set. The Caprini Risk Assessment Scale is an effective tool for predicting DVT risk in burn patients, aiding in risk stratification and targeted prophylaxis.

Introduction: Deep vein thrombosis (DVT) develops after lower limb arthroplasty despite the current use of prohylaxis. Thus, accurate risk stratification is warranted to establish new prophylactic strategies. Soleal vein (SV) dilatation is often found by ultrasonography, which is performd for the screeing of the DVT. However, if the SV dilatation is usable for prediction of the DVT after the lower limb arthroplasty remains unclear. Hypothesis: We aimed to examine whether the SV dilatation assessed by ultrasonography predicts the DVT after the lower limb arthroplasty. Methods: Ultrasonography was performed pre- (mean 5 days) and postoperatively (mean 8 days) in 135 osteoarthritic patients (age 66+/-13 years, 76% women) who underwent total hip arthroplasty (THA; n = 99) or knee arthroplasty (TKA; n = 36). The patients with preoperative DVT were excluded. Presence of DVT was diagnosed by ultrasonography, which was performed from the bilateral femoral to lower limb. Increased diameter of SV (&gt;10 mm) assessed by ultrasonography was defined as the SV dilatation. Results: Thirty seven patients (27%) developed the DVT, which was proximal in one (3%) and distal in 36 (97%), after the lower limb arthroplasty. SV dilation was observed in 14 patients (10%). Of these, 11 (79%) had the postoperative DVT. Multivariate logistic regression analysis indicated that age (odds ratio [OR] 1.1, 95% CI 1.01 to 1.11, p=0.016), female (OR 4.9, 95% CI 1.18 to 19.9, p=0.028), TKA (OR 2.7, 95% CI 1.01 to 7.37, p=0.047), and SV dilatation (OR 18.8, 95% CI 4.0 to 88.8, p&lt;0.001), but not presence of comorbidities, medications, operative time, plasma D-dimer value, independently predict postoperative DVT in the whole studied patients. Subgroup analyses according to the operation site demonstrated that the SV dilation was an independent predictor of postoperative DVT in the THA group (OR 11.1, 95% CI 2.1 to 59.0, p&lt;0.01), however, not in the TKA group. Conclusions: In addtion to well-known risk factors for postoperative DVT, the SV dilatation assessed by ultrasonography is an independent predictor of the DVT after the THA. Assessment of the SV diameter by ultrasonography is useful for identfying patients with high risk for the postoprtative DVT after the THA.

Objective To analyze the risk factors of lower limb deep vein thrombosis (DVT) following femoral shaft fracture. Methods A retrospective study was conducted to analyze the 67 patients with femoral shaft fracture who had been treated at our department from January 2011 to February 2014. They were 45 men and 22 women, 18 to 55 years of age. A positive result of venous contrast examination was taken as the gold standard for diagnosis of lower limb DVT. There were 18 patients in the DVT group (26.9%) and 49 in the non-DVT group (73.1%). The data were analyzed concerning general clinical information, fracture type, complications, vascular injury, D-dimer level, venous ultrasonography, venous contrast examination, anesthesia methods, operative methods, operation time and bleeding volume. The risk factors of DVT were determined using Logistic regression analysis. Results Complex fracture (OR=3.773, P=0.038), combined vascular injury (OR=2.603, P=0.002), increased D-dimer level (OR=1.697, P=0.002), and positive result of venous ultrasonography (OR=3.068, P< 0.001) were identified as the independent risk factors for lower limb DVT. Conclusions The major risk factors of lower limb DVT following femoral shaft fracture are complex fracture and vascular injury. The main screening methods of lower limb DVT are D-dimer level test and venous ultrasonography. Key words: Femoral fracture; Venous thrombosis; Risk factors

Successful monitoring of deep vein thrombosis (DVT) remains a challenging problem after gynecological laparoscopy. Thus, this study aimed to create and validate predictive models for DVT with the help of machine learning (ML) algorithms. A total of 489 patients from the Cancer Biology Research Center, Tongji Hospital were included in the study between January 2017 and February 2023, and 35 clinical indicators from electronic health records (EHRs) were collected within 24h of patient admission. Risk factors were identified using the least absolute shrinkage and selection operator (LASSO) regression. Then, the three commonly used DVT prediction models are random forest model (RFM), generalized linear regression model (GLRM), and artificial neural network model (ANNM). In addition, the predictive performance of various prediction models (i.e. the robustness and accuracy of predictions) is evaluated through the receiver operating characteristic curve (ROC) and decision curve analysis (DCA), respectively. We found postoperative DVT in 41 (8.38%) patients. Based on the ML algorithm, a total of 13 types of clinical data were preliminarily screened as candidate variables for DVT prediction models. Among these, age, body mass index (BMI), operation time, intraoperative pneumoperitoneum pressure (IPP), diabetes, complication and D-Dimer independent risk factors for postoperative DVT and can be used as variables in ML prediction models. The RFM algorithm can achieve the optimal DVT prediction performance, with AUC values of 0.851 (95% CI: 0.793-0.909) and 0.862 (95% CI: 0.804-0.920) in the training and validation sets, respectively. The AUC values of the other two prediction models (ANNM and GLRM) range from 0.697 (95% CI: 0.639-0.755) and 0.813 (95% CI: 0.651-0.767). In summary, we explored the potential risk of DVT after gynecological laparoscopy, which helps clinicians identify high-risk patients before gynecological laparoscopy and make nursing interventions. However, external validation will be needed in the future.

Venous thromboembolism (VTE) is a potentially fatal perioperative complication. Understanding the risk factors for deep vein thrombosis (DVT) and initiating appropriate prophylaxis is pivotal for reducing the risk of VTE. The purpose of this study was to clarify the perioperative risk factors for DVT in patients undergoing surgery for gastric cancer. We reviewed the findings of lower limb ultrasonography performed in 160 patients who underwent gastrectomy for gastric cancer. The preoperative and postoperative incidence of DVT was 4.4% (7/160) and 7.2% (11/153), respectively. All postoperative DVTs were of the distal type, whereas preoperative DVTs were of the proximal (n = 3) and distal type (n = 4). None of the patients suffered symptomatic VTE. Multivariate analysis indicated that depth of invasion and D-dimer concentration were independent risk factors for preoperative DVT and that gender and performance status were risk factors for postoperative DVT. Receiver operating characteristic analysis revealed that the optimal cut-off D-dimer concentration was 1.4μg/mL. The incidence of perioperative DVT was low for patients undergoing gastric cancer surgery. Therefore, the risk-stratified application of perioperative pharmacologic thromboprophylaxis is thought to be more appropriate than routine pharmacologic thromboprophylaxis for Japanese patients undergoing surgery for gastric cancer.