Postoperative renal function evaluation, through RIFLE criteria, of elderly patients who underwent femur fracture surgery under spinal anesthesia

Prediction of acute kidney injury in patients with femoral neck fracture utilizing machine learning

Background

Acute kidney injury (AKI) is a common complication associated with significant morbidity and mortality in high-energy trauma patients. Given the poor efficacy of interventions after AKI development, it is important to predict AKI before its diagnosis. Therefore, this study aimed to develop models using machine learning algorithms to predict the risk of AKI in patients with femoral neck fractures.

Methods

We developed machine-learning models using the Medical Information Mart from Intensive Care (MIMIC)-IV database. AKI was predicted using 10 predictive models in three-time windows, 24, 48, and 72 h. Three optimal models were selected according to the accuracy and area under the receiver operating characteristic curve (AUROC), and the hyperparameters were adjusted using a random search algorithm. The Shapley additive explanation (SHAP) analysis was used to determine the impact and importance of each feature on the prediction. Compact models were developed using important features chosen based on their SHAP values and clinical availability. Finally, we evaluated the models using metrics such as accuracy, precision, AUROC, recall, F1 scores, and kappa values on the test set after hyperparameter tuning.

Results

A total of 1,596 patients in MIMIC-IV were included in the final cohort, and 402 (25%) patients developed AKI after surgery. The light gradient boosting machine (LightGBM) model showed the best overall performance for predicting AKI before 24, 48, and 72 h. AUROCs were 0.929, 0.862, and 0.904. The SHAP value was used to interpret the prediction models. Renal function markers and perioperative blood transfusions are the most critical features for predicting AKI. In compact models, LightGBM still performs the best. AUROCs were 0.930, 0.859, and 0.901.

Conclusions

In our analysis, we discovered that LightGBM had the best metrics among all algorithms used. Our study identified the LightGBM as a solid first-choice algorithm for early AKI prediction in patients after femoral neck fracture surgery.

Predictors of postoperative acute kidney injury in patients undergoing hip fracture surgery: A systematic review and meta-analysis

BACKGROUND

The present study aimed to summarize the predictors of acute kidney injury (AKI) in patients after hip surgery.

METHODS

A literature search was performed using PubMed, EMBASE, Cochrane Library, and Web of Science for studies assessing the predictors of AKI after hip fracture surgery. Pooled odds ratio (OR) and mean difference (MD) of those who experienced AKI compared to those who did not were calculated for each variable. Evidence was assessed using the Newcastle-Ottawa Scale.

RESULTS

Ten studies with 34 potential factors were included in the meta-analysis. In the primary analysis, 12 factors were associated with AKI, comprising males (OR 1.25; 95% confidence interval (CI) 1.14-1.36), advanced age (MD 2.28; 95% CI 0.80-3.75), myocardial infarction (OR 1.39; 95% CI 1.18-1.63), hypertension (OR 1.46; 95% CI 1.13-1.89), diabetes (OR 1.84; 95% CI 1.40-2.42), chronic kidney disease (OR 3.66; 95% CI 2.21-6.07), hip arthroplasty (OR 1.35; 95% CI 1.22-1.50), angiotensin-converting enzyme inhibitors/angiotensin receptor blockers use (OR 2.28; 95% CI 1.68-3.08), more intraoperative blood loss (MD 44.06; 95% CI 2.88-85.24), higher preoperative blood urea nitrogen levels (MD 5.29; 95% CI 3.38-7.20), higher preoperative serum creatinine levels (MD 0.4; 95% CI 0.26-0.53), and lower preoperative estimated glomerular filtration rate (MD -19.59; 95% CI -26.92--12.26). Another 13 factors related to AKI in individual studies were identified in the systematic review.

CONCLUSION

Related prophylaxis strategies should be implemented in patients involved with the above-mentioned characteristics to prevent AKI after hip surgery.

Factors associated with postoperative acute kidney injury after hip fractures in elderly patients

OBJECTIVES

Acute kidney injury (AKI) is a rare but serious complication after hip fractures. The aim of this study was to evaluate the incidence and the risk factors of postoperative AKI after hip fractures.

METHODS

From January 2011 to December 2016, 550 patients who underwent surgery of hip fractures at our institution were retrospectively reviewed. AKI was defined and classified by AKI Network (AKIN) Classification/Staging System. The incidence, mortality, and risk factors of postoperative AKI were investigated. Receiver operating characteristic curve analysis was conducted to evaluate the ability of markers in predicting AKI.

RESULTS

The incidence of postoperative AKI was 4.4% (25 cases). The mean onset of postoperative AKI was 8.0 ± 5.3 days and recovered after 7.0 ± 4.2 days after the occurrence of AKI. Of 25 patients with AKI, 6 patients (24.0%) died within 1 year after surgery. The independent risk factors for postoperative AKI are the estimated blood loss (EBL) (odds ratio (OR) 1.64; 95% confidence interval (CI) 1.33-2.58; p < 0.01) and postoperative level of albumin (OR 1.77; 95% CI 1.52-2.74; p < 0.01). The cutoff value of the serum albumin was <2.8 g/dL with a sensitivity of 88.0% and a specificity of 77.1%. The cutoff value of EBL was <766.5 mL with a sensitivity of 84.0% and a specificity of 66.3%.

CONCLUSION

Postoperative AKI after hip fractures had low incidences (4.4%) but high mortality (24.0%). The postoperative AKI was correlated with blood loss and low postoperative albumin levels.

ACUTE KIDNEY INJURY FOLLOWING SURGERY FOR HIP FRACTURE

Objective:

An observational study was carried out to determine the rate of acute kidney injury (AKI) following surgery for hip fracture at our institution and to look for factors associated with AKI.

Methods:

Preoperative creatinine values were compared to post-operative results for all patients who underwent surgery for hip fracture at our institution between 1^st January 2015 and 30^th September 2016. AKI was defined as an increase in postoperative creatinine, greater than or equal to 1.5 times the preoperative value within 7 days. Chi-squared test and Student’s t-test were used to look for factors associated with AKI.

Results:

Out of 500 patients, 96 developed an AKI (19.2%). Patients with chronic kidney disease (CKD) were more likely to develop AKI (30.8%) that those without it (17.2%, p = 0.018). Similarly, patients with 2 or more comorbidities were more likely to develop AKI (22.0%) than those without it (12.4%, p = 0.009). No statistically significant association was observed between type of surgery and AKI.

Conclusion:

A large proportion of patients following surgery for hip fracture developed AKI. Patients with CKD and the presence of 2 or more comorbidities had significantly higher rates of AKI. Level III evidence, Retrospective comparative study.

Acute kidney injury following hip fracture

BACKGROUND

Hip fracture causes disability and excess mortality in the aging population. Acute kidney injury (AKI), is known to diminish survival of critically ill and trauma patients. AKI is also a common perioperative complication among surgical patients. We examined the effect of AKI on the survival of hip fracture patients in a Finnish hip fracture population and the risk factors for AKI in a prospective study.

METHODS

The study cohort constituted of 486 consecutive low-energy trauma hip fracture patients referred to Satakunta Central Hospital (Pori, Finland) and Turku University Hospital (Turku, Finland). The patients underwent standard diagnostics and treatment in the emergency department (ER) and were operated according to the local treatment protocol. Serum creatinine (sCr) was analyzed daily pre- and post-operatively during the hospital stay. Patients were divided into groups; AKI and non-AKI based on Kidney Disease: Improving Global Outcomes (KDIGO) criteria.

RESULTS

The incidence of AKI in the study cohort was 8.4% (40/475). Eleven patients were excluded due to missing sCr data. The baseline characteristics of AKI and non-AKI groups differed significantly concerning baseline sCr but were otherwise similar. At 90-day follow-up, the overall mortality was 14.4%. Patients with AKI had a significantly higher mortality (35.0%) than those with no AKI (12.7%) (p < 0.001). Dementia, preoperative sCr and any stage of AKI were independent predictors for mortality. Dementia and preoperative sCr were independently associated with post-operative AKI.

CONCLUSION

In this study AKI was a significant factor associated with a 3 -fold mortality during the first three months after surgery for low-energy trauma hip fracture.

The Correlation between Preoperative and Postoperative Hypoalbuminaemia and the Development of Acute Kidney Injury with Respect to the KDIGO Criteria in the Hip Fracture Surgery in Elderly Patients

Objective

The aim of the present study was to determine the correlation between preoperative and postoperative hypoalbuminaemia and acute kidney injury (AKI) in the hip fracture surgery in elderly patients.

Methods

A total of 160 patients aged ≥65 years were scanned retrospectively. They were grouped into four as the preoperative albumin level of <3.8, preoperative albumin level of >3.8, postoperative day 2 albumin level of <2.9 and postoperative day 2 albumin level of >2.9. In the beginning and 7 days, age, gender, white blood cell, haemoglobin, haematocrit, glucose, blood urea nitrogen, serum creatinine, albumin values, fever, anaesthesia method, presence of blood transfusion, surgical period, hospitalisation durations and expenses in the postoperative period were recorded for all the patients.

Results

In the study, 92 women and 68 men were scanned. AKI was observed in 28 (17.5%) patients, and 16 (57.1%) patients were determined in stage 1. AKI development in Group 1 and Group 3 was significantly high (p<0.05). Advanced age, multiple drug usage, postoperative glucose level and blood product transfusion during the operation were significantly associated with AKI (p<0.05). The hospitalisation period and cost were high in patients with AKI (p<0.05).

Conclusion

It was determined that hypoalbuminaemia was associated with AKI development, and preoperative or postoperative hypoalbuminaemia affected AKI development at similar rates. Advanced age, multiple drug usage, postoperative glucose level and blood product transfusion during the operation were associated with AKI.

Early postoperative hypoalbuminemia is a risk factor for postoperative acute kidney injury following hip fracture surgery

INTRODUCTION

Acute kidney injury (AKI) is a common and serious complication after hip fracture surgery in older adults. Hypoalbuminemia is a known independent risk factor for AKI. However, few studies have investigated the relationship between early postoperative hypoalbuminemia and AKI after hip fracture surgery. Therefore, we sought to determine the incidence of and risk factors for AKI and the effects of early postoperative hypoalbuminemia on AKI incidence after surgery for hip fractures, especially intertrochanteric fractures of the proximal femur.

PATIENTS AND METHODS

In this retrospective cohort study from a single center, we reviewed the medical records of 481 consecutive patients (>60 years) who underwent surgery for intertrochanteric fracture of the proximal femur. Multiple logistic regression was performed to identify independent risk factors for AKI. After determining the cut-off value of the minimal level of postoperative serum albumin during the first two postoperative days, we divided the patients into two groups: group 1 included 251 patients whose minimal early postoperative serum albumin level was <2.9 g/dL during the first two postoperative days; and group 2 included 230 patients whose minimal early postoperative serum albumin level was ≥2.9 g/dL. The incidence of AKI was analyzed using inverse probability of treatment weighting (IPTW), propensity score matching (PSM), and propensity score matching weighting (PSMW) analyses.

RESULTS

The incidence of AKI, defined based on the Kidney Disease Improving Global Outcomes criteria, was 11.8% (n = 57). Chronic kidney disease and the minimal early postoperative serum albumin level <2.9 g/dL at any point during the first two postoperative days were independent risk factors for AKI. The IPTW, PSM, and PSMW analyses comparing the incidence of AKI between the two groups revealed that the minimal early postoperative serum albumin level <2.9 g/dL was significantly associated with AKI development (P < 0.001, P = 0.025, and P = 0.011, respectively).

CONCLUSION

The incidence of postoperative AKI was 11.8%. Our findings demonstrate that early postoperative hypoalbuminemia is an independent risk factor for AKI in patients undergoing surgery for intertrochanteric fracture of the proximal femur.

Risk of acute renal failure and mortality after surgery for a fracture of the hip

Aims

We examined risk of developing acute renal failure and the associated mortality among patients aged > 65 years undergoing surgery for a fracture of the hip.

Patients and Methods

We used medical databases to identify patients who underwent surgical treatment for a fracture of the hip in Northern Denmark between 2005 and 2011. Acute renal failure was classified as stage 1, 2 and 3 according to the Kidney Disease Improving Global Outcome criteria. We computed the risk of developing acute renal failure within five days after surgery with death as a competing risk, and the short-term (six to 30 days post-operatively) and long-term mortality (31 days to 365 days post-operatively). We calculated adjusted hazard ratios (HRs) for death with 95% confidence intervals (CIs).

Results

Among 13 529 patients who sustained a fracture of the hip, 1717 (12.7%) developed acute renal failure post-operatively, including 1218 (9.0%) with stage 1, 364 (2.7%) with stage 2, and 135 (1.0%) with stage 3 renal failure. The short-term mortality was 15.9% and 5.6% for patients with and without acute renal failure, respectively (HR 2.8, 95% CI 2.4 to 3.2). The long-term mortality was 25.0% and 18.3% for those with and without acute renal failure, respectively (HR 1.3, 95% CI 1.2 to 1.5). The mortality was higher in patients with an increased severity of renal failure.

Conclusion

Acute renal failure is a common complication of surgery in elderly patients who sustain a fracture of the hip, and is associated with increased mortality up to one year after surgery despite adjustment for coexisting comorbidity and medication before surgery. Cite this article: Bone Joint J 2016;98-B:1112–18.

Risk factors for acute kidney injury after hip fracture surgery in the elderly individuals

OBJECTIVE

We aimed to evaluate possible risk factors assocıated wıth acute kidney injury (AKI) after hip fracture surgery in the elderly individuals.

DESIGN

Level II diagnostic study, evidence obtained from prospective cohort study from 1 center with level 2, and 3 patients.

PATIENTS

A total of 165 patients (>65 years) with femoral neck fracture were enrolled in this prospective study between 2007 and 2010. Two patients were dropped for inadequate laboratory follow-up data. Patients with kidney failure or renal replacement therapy (RRT) history or AKI at admission were excluded.

INTERVENTION

Nephrology consultation was obtained from all patients at admission. All patients had undergone bipolar cemented hip arthroplasty that was performed by the same surgical team in all patients within 24 hours of fracture and admission under the same protocol.

MAIN OUTCOME MEASUREMENTS

Serum creatinine (SCr), urine output, and complete blood counts were evaluated at baseline and daily basis thereafter. The AKI was defined based on Acute Kidney Injury Network classification. Hospital charges were converted from Turkish Liras to US dollars and rounded.

RESULTS

Among 163 patients, AKI occurred in 25 (15.3%) patients, all within the first 48 postoperative hours. Three (1.8%) patients required RRT. Baseline SCr levels were restored within 4.84 ± 1.34 days on average (3-8 days). No patient required RRT after discharge. The mean hospital stay was 3 days (2-6 days) longer and the hospital charge was 2500 US$ higher for the patients with AKI. After multivariable adjustment, only lower estimated glomerular filtration rate levels (odds ratio 0.945, 95%confidence interval 0.92-0.96) emerged as an independent predictor for AKI.

CONCLUSION

The AKI represents a frequent complication after hip fracture surgery associated with longer hospital stay and higher treatment costs with increased morbidity. Our results show baseline renal function is an independent predictor of AKI.

Risk factors of acute kidney injury according to RIFLE criteria after lung cancer surgery

BACKGROUND

Perioperative acute kidney injury (AKI) is associated with increased mortality and morbidity. Our aim was to evaluate the incidence and determinants of AKI using the risk, injury, failure, loss of function, and end-stage kidney disease (RIFLE) criteria in thoracic surgical patients.

METHODS

We retrospectively analyzed a cohort of patients undergoing lung cancer surgery from 1996 to 2009. Patient management was protocol-driven, and postoperative complications were prospectively collected. The primary outcome was AKI within 3 days after surgery. A variety of patient comorbidities and operative characteristics were evaluated as potential predictors of AKI using a multiple logistic regression model.

RESULTS

Complete data were obtained from 1,345 patients, and the incidence of AKI was 6.8%. Four independent risk factors for AKI were identified: American Society of Anesthesiologists classes 3 and 4 (odds ratio [OR] 2.60, 95% confidence interval [CI]: 1.03 to 6.55), forced expiratory volume in 1 second (OR 0.55, 95% CI: 0.32 to 0.96), the use of vasopressors (OR 1.015, 95% CI: 0.998 to 1.035), and the duration of anesthesia (OR 1.044, 95% CI: 1.001 to 1.008). Patients who experienced AKI were more frequently admitted to the intensive care unit (24.2% versus 3.5% for patients without AKI, p < 0.05); they had increased mortality (19.8% versus 1.1%, p < 0.05) and a threefold to fourfold higher incidence of cardiopulmonary complications.

CONCLUSIONS

The RIFLE classification is a valuable tool to assess AKI after lung cancer surgery. The severity of perioperative renal impairment is associated with increased mortality and morbidity.