Sustained Postoperative Fever Without Evident Cause After Spine Instrumentation as an Indicator of Surgical Site Infection

Explainable Machine Learning Models for Prediction of Surgical Site Infection After Posterior Lumbar Fusion Surgery Based on Shapley Additive Explanations

OBJECTIVE

This study aims to develop machine learning (ML) models combined with an explainable method for the prediction of surgical site infection (SSI) after posterior lumbar fusion surgery.

METHODS

In this retrospective, single-center study, a total of 1016 consecutive patients who underwent posterior lumbar fusion surgery were included. A comprehensive dataset was established, encompassing demographic variables, comorbidities, preoperative evaluation, details related to diagnosed lumbar disease, preoperative laboratory tests, surgical specifics, and postoperative factors. Utilizing this dataset, 6nullML models were developed to predict the occurrence of SSI. Performance evaluation of the models on the testing set involved several metrics, including the receiver operating characteristic curve, the area under the receiver operating characteristic curve, accuracy, recall, F1 score, and precision. The Shapley Additive Explanations (SHAP) method was employed to generate interpretable predictions, enabling a comprehensive assessment of SSI risk and providing individualized interpretations of the model results.

RESULTS

Among the 1016 retrospective cases included in the study, 36 (3.54%) experienced SSI. Out of the six models examined, the Extreme Gradient Boost model demonstrated the highest discriminatory performance on the testing set, achieving the following metrics: precision (0.9000), recall (0.8182), accuracy (0.9902), F1 score (0.8571), and area under the receiver operating characteristic curve (0.9447). By utilizing the SHAP method, several important predictors of SSI were identified, including the duration of indwelling jugular vein catheter, blood urea nitrogen levels, total protein levels, sustained fever, creatinine levels, triglycerides levels, monocyte count, diabetes mellitus, drainage time, white blood cell count, cerebral infarction, estimated blood loss, prealbumin levels, Prognostic Nutritional Index, low back pain, posterior fusion score, and osteoporosis.

CONCLUSIONS

ML-based prediction tools can accurately assess the risk of SSI after posterior lumbar fusion surgery. Additionally, ML combined with SHAP could provide a clear interpretation of individualized risk prediction and give physicians an intuitive comprehension of the effects of the model's essential features.

Postoperative fever following surgery for oral cancer: Incidence, risk factors, and the formulation of a machine learning-based predictive model

BACKGROUND

Postoperative fever (POF) is a common occurrence in patients undergoing major surgery, presenting challenges and burdens for both patients and surgeons yet. This study endeavors to examine the incidence, identify risk factors, and establish a machine learning-based predictive model for POF following surgery of oral cancer.

METHODS

A total of seven hundred and twenty-seven consecutive patients undergoing radical resection of oral cancer were retrospectively investigated. The analysis encompassed 34 parameters, incorporating demographic and clinical characteristics, biochemical and hematological assay results, surgical-related data, hospitalization costs and stay in hospital. Six machine learning models were compared by the area under the receiver operating characteristic curve (AUC). The best-performing models were selected for further analyze, including feature importance evaluation and nomogram analysis, identifying key POF risk factors, and establish a comprehensive prediction model.

RESULTS

A total of 466 patients with surgery for oral cancer met the criteria, with an average age of (54.2 ± 11.1) years, including an POF group (n = 197) and a non-POF group (n = 269). The fever group has greater hospitalization costs, longer lengths of stay, and higher infection biochemical indicators (leucocyte ratio and erythrocyte sedimentation rate). Furthermore, Among the 6 machine learning models, logistic regression models performed best, with the higher AUC and accuracy. In univariate and multivariate logistic analysis showed that age, sex, reoperation, Charlson Comorbidity Index score (CCI), leukocyte, bleeding and blood transfusion were independent risk factors for POF of patients following surgery in oral cancer. Then seven variables were selected to establish the nomogram for predict the probability of POF by nomogram algorithm.

CONCLUSIONS

Postoperative fever patients following radical resection of oral cancer have greater burden. Machine learning algorithms can be effectively used to identify potential risk factors of POF, which may enhance individualized treatment plans in oral cancer patient during perioperative period.

Early Intervention in Post-operative Infectious Spondylodiscitis: Outcome of Aggressive Transforaminal Lumbar Interbody Fusion

Introduction

Conservative and surgical approach timeline in post-operative spondylodiscitis (POS) following lumbar disc herniation (LDH) surgery is ill defined, and patients have a protracted recovery phase with social, psychological, and financial implications.

Material and Methods

Retrospective analysis of patients operated by transforaminal lumbar interbody fusion (TLIF) in POS was done. Confirmed clinico-radiological diagnosed POS cases, not responding within three to four weeks were included. Normalisation of CRP and radiological stable reconstruction was assessed for objective clearance of POS and bony union.

Results

Ninety-five patients were included in the study with minimum follow-up period of two years. The mean age was 51.63±13.63 years. There were organisms cultured in 55 patients (57.89%). The ODI improvement of the patients was noted to improve from 88.71±5.3 to 20.80±9.7 (8 weeks) and was incremental at 2 years follow-up (10.12±6.41) and maintained further at final follow-up at 9±4.3. Bony union achieved in all with stable reconstruction. The resumption of activities of daily living (ADL) was quick (15.90±8.20 days) and job (3.67±1.31 months) was achieved in all the patients. In poor outcomes, two patients didn't respond, and one patient died due to uncontrolled infection.

Conclusion

Early diagnosis and intervention is the key to effective management of POS. Utilisation of aggressive TLIF yields faster ADL resumption.

Temperature Measurement Timings and the Fever Detection Rate After Gastrointestinal Surgery: Retrospective Cross-Sectional Study

BACKGROUND

Postoperative fever frequently indicates surgical complications and is commonly used to evaluate the efficacy of interventions against surgical stress. However, the presence of circadian rhythms in body temperature may compromise the accurate detection of fever.

OBJECTIVE

This study aimed to investigate the detection rate of fever under intermittent measurement.

METHODS

We retrospectively reviewed the clinical records of patients who underwent nonemergency gastrointestinal surgery between November 2020 and April 2021. Patients' temperature data were continuously collected every 4 seconds using a wireless axillary thermometer, and fever was defined as a temperature exceeding 38 °C within a day. To simulate intermittent measurement in clinical practice, the body temperature at each hour was selected from the continuously collected temperature dataset. Considering that temperatures are measured multiple times per day, all possible measurement plans using intermittent measurement were composed by combining 1-24 time points from the 24-hour daily cycle. Fever was clinically diagnosed based on the temperature readings at the selected time points per day. The fever detection rates for each plan, with varying measurement times, were listed and ranked.

RESULTS

Based on the temperature data continuously collected by the thermometer, fever occurred in 60 (40.8%) of the 147 included patients within 3 days after surgery. Of the measurement plans that included 1-24 measurements daily, the fever detection rates ranged from 3.3% (2/60) to 85% (51/60). The highest detection rates and corresponding timings for measurement plans with 1, 2, 3, and 4 measurements daily were 38.3% (23/60; at 8 PM), 56.7% (34/60; at 3 AM and 7 or 8 PM), 65% (39/60; at 3 AM, 8 PM, and 10 or 11 PM), and 70% (42/60; at 12 AM, 3 AM, 8 PM, and 11 PM), respectively; and the lowest detection rates were 3.3% (2/60), 6.7% (4/60), 6.7% (4/60), and 8.3% (5/60), respectively. Although fever within 3 days after surgery was not correlated with an increased incidence of postoperative complications (5/60, 8.3% vs 6/87, 6.9%; P=.76), it was correlated with a longer hospital stay (median 7, IQR 6-9 days vs median 6, IQR 5-7 days; P<.001).

CONCLUSIONS

The fever detection rate of the intermittent approach is determined by the timing and frequency of measurement. Measuring at randomly selected time points can miss many fever events after gastrointestinal surgery. However, we can improve the fever detection rate by optimizing the timing and frequency of measurement.

Logistic regression model predicts early surgical site infection after spinal fusion: a retrospective cohort study

OBJECTIVE

This study aimed to develop a diagnostic model for predicting early surgical site infection (SSI) based on postoperative inflammatory markers after spinal fusion surgery.

METHODS

In this retrospective study, we analysed the trends of inflammatory markers between SSI and non-SSI groups. The data were randomly divided into training cohort and validation cohort (ratio 7:3). The variables for SSI were analysed using stepwise logistic regression to develop the prediction model. To evaluate the model, we analysed its sensitivity, specificity, positive predictive value, negative predictive value, as well as the area under the curve in the validation cohort. Calibration plots and decision curve analysis were employed to assess the calibration and clinical usefulness of the model.

FINDINGS

We observed significant changes in inflammatory markers on the seventh day after surgery. The prediction model included four variables on the seventh day after surgery: body temperature, C-reactive protein, erythrocyte sedimentation rate and neutrophil counts. After binary processing of these data, the simplified model achieved an area under the curve of 0.86 (95% confidence interval (CI): 0.81-0.92) in the training cohort and 0.9 (95% CI: 0.82-0.98) in the validation cohort. Calibration plots and decision curve analysis demonstrated that the proposed model was effective for the diagnosis of SSI.

CONCLUSION

We developed and validated a prediction model for diagnosing early infection after spinal fusion.

Preemptive QP001, a fast-acting meloxicam formulation, provides analgesia and reduces opioid consumption following abdominal surgery: a randomized controlled trial

BACKGROUND

QP001, a novel meloxicam formulation, has been developed to manage moderate to severe postoperative pain. This study aimed to evaluate the efficacy and safety of QP001 injections for moderate to severe pain following abdominal surgery.

METHOD

This prospective, multicenter, randomized, double-blind, placebo-controlled clinical trial enlisted patients experiencing moderate to severe pain following abdominal surgery. These patients were randomized to receive either QP001 injections (30 mg or 60 mg) or a placebo pre-surgery. The primary efficacy endpoint was the total morphine consumption within 24 h after the first administration.

RESULTS

A total of 108 patients were enrolled, and 106 patients completed the study. The total morphine consumption in the QP001 30 mg group and 60 mg group, versus placebo group, were significantly lower over the following 24 h (5.11[5.46] vs 8.86[7.67], P = 0.011; 3.11[3.08] vs 8.86[7.67], P < 0.001), respectively. The total morphine consumption in the QP001 30 mg and 60 mg groups, versus placebo group, was also significantly decreased over the following 48 h, including the 24-48 h period (P ≤ 0.001). The QP001 30 mg and 60 mg groups, versus placebo, showed a significant decrease in the area under the curve for pain intensity-time as well as a significant decrease in the effective pressing times of the analgesic pump over the 24 h and 48 h periods (P < 0.05). The QP001 groups, versus placebo, show no significant different in Adverse Events or Adverse Drug Reactions (P > 0.05).

CONCLUSION

Preoperative/preemptive QP001 provides analgesia and reduces opioid consumption in patients with moderate to severe pain following abdominal surgery, while maintaining a favorable safety profile.

:

Background

We aimed to determine the prevalence and risk factors of surgical site infection (SSI) after cesarean delivery (CD) in a rural area in China.

Methods

We identified 155 patients with incisional and organ/space SSIs by International Classification of Disease codes and matched them with 465 patients (controls) in a time-matched retrospective quality assurance analysis. Multiple logistic regression analyses were performed to examine the risk factors for SSI: the work-years of providers, the number of antenatal care (ANC) visits, CD after labor, positive discharge culture, postoperative C-reactive protein (CRP) levels and fever.

Results

and discussion: During the study, 155 women with SSI were identified among the 8640 patients who delivered by CD. The incidence of SSIs was 179 per 10 000patients (95%CI: 151–207 per 10 000 patients). The total duration of hospitalization in patients with SSI was 14.49 ± 8.68 days compared with 7.96 ± 2.35 days in patients with no SSI (P < 0.01). Multiple logistic regression analysis showed that the work-years of providers (odds ratio [OR] = 3.729, 95% confidence interval [CI]: 1.463–9.501, p = 0.006), irregular ANC visits (OR = 3.245, 95% CI: 1.264–8.329, p = 0.028), CD after labor (OR = 2.545, 95% CI: 0.935–6.926, p = 0.020), postoperative CRP level (OR = 2.545, 95% CI: 0.935–6.926, p = 0.016) and a positive discharge culture (OR = 2.954, 95% CI: 0.305–28.643, p = 0.019) were positively associated with SSI. However, the rates of maternal request (OR = 0.186, 95% CI: 0.065–0.535, p = 0.002) and postoperative fever (OR = 0.208, 95% CI: 0.087–0.494, p = 0.001) were negatively related to SSI.

Conclusions

Special attentions should be paid to CD patients who had irregular ANC visits, attempted labor, a positive discharge culture, higher CRP levels and fever after surgery, who had a greater risk of SSI.

•

The incidence of SSIs was 179 per 10 000 patients (95%CI: 151–207).

•

Risk factors of SSIs included: irregular ANC visits, a positive discharge culture.

•

Higher CRP levels and fever after surgery had a greater risk of SSI.

[Study of modified subcutaneous lumbar spine index as a predictor for short-term effectiveness in transforaminal lumbar interbody fusion]

Objective

To explore the value of modified subcutaneous lumbar spine index (MSLSI) as a predictor for short-term effectiveness of transforaminal lumbar interbody fusion (TLIF) in treatment of lumbar degenerative disease (LDD).

Methods

Between February 2014 and October 2019, 450 patients who were diagnosed as LDD and received single-segment TLIF were included in the study. Based on the MSLSI measured by preoperative lumbar MRI, the patients were sorted from small to large and divided into three groups ( n=150). The MSLSI of group A was 0.11-0.49, group B was 0.49-0.73, and group C was 0.73-1.88. There was no significance in gender, age, disease duration, diagnosis, surgical segment, and improved Charlson comorbidity index between groups ( P>0.05). There were significant differences in the subcutaneous adipose depth of the L ₄ vertebral body and body mass index (BMI) between groups ( P<0.05). The operation time, intra-operative blood loss, length of incision, drainage tube placement time, drainage volume on the 1st day after operation, drainage volume on the 2nd day after operation, total drainage volume, antibiotic use time after operation, walking exercise time after operation, hospital stay, the incidences of surgical or non-surgical complications in the three groups were compared. Pearson correlation analysis was used to analyze the correlation between MSLSI and BMI, and partial correlation analysis was used to study the relationship between MSLSI, BMI, improved Charlson comorbidity index, subcutaneous adipose depth of the L ₄ vertebral body and complications. The Receiver Operating Characteristic (ROC) curve was used to evaluate the value of SLSI and MSLSI in predicting the occurrence of complications after TLIF in treatment of LDD.

Results

There was no significant difference in operation time, length of incision, antibiotic use time after operation, walking exercise time after operation, drainage tube placement time, drainage volume on the 1st day after operation, drainage volume on the 2nd day after operation, and total drainage volume between groups ( P>0.05). The amount of intra-operative blood loss in group C was higher than that in groups A and B, and the hospital stay was longer than that in group B, with significant differences ( P<0.05). Surgical complications occurred in 22 cases (14.7%), 25 cases (16.7%), and 39 cases (26.0%) of groups A, B, and C, respectively. There was no significant difference in the incidence between groups ( χ ²=0.826, P=0.662). The incidences of nerve root injury and wound aseptic complications in group C were higher than those in groups A and B, and the incidence of nerve root injury in group B was higher than that in group A, with significant differences ( P<0.05). There were 13 cases (8.7%), 7 cases (4.7%), and 11 cases (7.3%) of non-surgical complications in groups A, B, and C, respectively, with no significant difference ( χ ²=2.128, P=0.345). There was no significant difference in the incidences of cardiovascular complications, urinary system complications, central system complications, and respiratory system complications between groups ( P>0.05). There was a correlation between MSLSI and BMI in 450 patients ( r=0.619, P=0.047). Partial correlation analysis showed that MSLSI was related to wound aseptic complications ( r=0.172, P=0.032), but not related to other surgical and non-surgical complications ( P>0.05). There was no correlation between BMI, improved Charlson comorbidity index, subcutaneous adipose depth of the L ₄ vertebral body and surgical and non-surgical complications ( P>0.05). ROC curve analysis showed that the area under ROC curve (AUC) of MSLSI was 0.673 (95%CI 0.546-0.761, P=0.025), and the AUC of SLSI was 0.582 (95%CI 0.472-0.693, P=0.191).

Conclusion

MSLSI can predict the short-term effectiveness of TLIF in treatment of LDD. Patients with high MSLSI suffer more intra-operative blood loss, longer hospital stay, and higher incidence of nerve root injury and postoperative incision complications.