A Nomogram to Predict Delirium after Hip Replacement in Elderly Patients with Femoral Neck Fractures

Comparison of machine learning and logistic regression models for predicting emergence delirium in elderly patients: A prospective study

OBJECTIVE

To compare the performance of machine learning and logistic regression algorithms in predicting emergence delirium (ED) in elderly patients.

METHODS

A prospective study was carried out in a Chinese teaching tertiary hospital and collected the details of 1045 patients who underwent noncardiac surgery with general anesthesia. Characteristic variables related to ED were selected by least absolute shrinkage and selection operator (LASSO). Finally, seven machine learning models (gradient boosting machine, extreme gradient boosting, light gradient boosting machine, support vector machine, decision tree, neural network, and random forest) and logistic regression were used in the training set, and the predictive performance of the models was validated in the test set.

RESULTS

ED was identified in 316 (30.2%) patients. The logistic regression model performed better than the machine learning models (area under the curve [AUC] of 0.790, 95% confidence interval [CI] 0.736-0.843). Besides, the calibration curve indicated good consistency between predicted and actual ED probabilities, and decision curve analysis demonstrated that the logistic regression model could bring clinical benefits.

CONCLUSION

The optimal application of logistic regression can provide rapid and efficient risk prediction of ED for medical workers so that reasonable prevention and treatment measures can be taken.

Risk factors for postoperative delirium in patients undergoing orthopedic procedures: a systematic review and meta-analysis

Delirium is a common complication in surgical patients following operative procedures; it often occurs in patients undergoing lower-extremity surgery. It is essential to identify and prevent the risk factors for postoperative delirium (POD) in these cases. We aimed to determine the risk factors for POD in patients who underwent lower-extremity surgery through a systematic review and meta-analysis. We included observational studies identifying risk factors for POD in patients undergoing orthopedic surgery. Data sources included the Cumulative Index to Nursing and Allied Health Literature and MEDLINE. We extracted the variables related to delirium that were analyzed by two or more studies meeting the eligibility criteria. A random-effects model was used to calculate the pooled odds ratio, standardized mean difference, and 95% confidence interval. Data were considered significant when p <  0.05. Twenty-seven studies with a total sample size of 9,044 were evaluated. Our meta-analysis revealed 20 risk factors for patients with POD undergoing orthopedic surgery, including age, cognitive scores, various preoperative laboratory values (such as serum albumin, C-reactive protein, and thyroid hormones), length of hospital stay, surgery and anesthesia duration, blood transfusion, and previous health conditions such as dementia and cardiovascular disease. Gathering preoperative and postoperative data was crucial for identifying high-risk patients for POD. In addition, preventive measures targeting POD risk factors could reduce its occurrence after orthopedic surgery.

[Translated article] Hip fractures in Spain. How are we? Systematic review and meta-analysis of the published registries

OBJECTIVE

Spain is expected to be the country with the highest life expectancy in the coming years. In this context, it is important to improve the care of hip fractures. The objective of this work was to describe the results of the registries published on hip fractures in Spain.

MATERIAL AND METHODS

Systematic review and meta-analysis of the records published on hip fractures in Spain, the last 10 years. The characteristics of the study, characteristics of the patients, of the fractures, the type of surgery, as well as morbidity and mortality were analyzed.

RESULTS

A total of 55,680 patients with a mean age of 84.6 years were analyzed, of whom 75% were women. Extracapsular fractures were the most frequent (58%). It was found that conservative treatment was applied in an average of 3% of cases. The average surgical delay was 64.7h, with a mean percentage of patients operated on within 24h at 18%, and within 48h at 40%. A mean hospitalization time of 10.7 days was found. Delirium was found to be the most frequent postoperative complication (42%). The mean transfusion rate was 36%. Mean in-hospital mortality at one month and one year was 4%, 5% and 18%, respectively.

CONCLUSIONS

Less than half of patients with a hip fracture undergo surgery within 48h, despite being recommended by the majority of clinical practice guidelines. Delirium is the most frequently reported postoperative complication, and one in every 5 patients will die within a year after a hip fracture. Standardizing the management of hip fractures at the state level could improve healthcare quality and facilitate the establishment of common criteria for good clinical practice.

Development of a LASSO machine learning algorithm-based model for postoperative delirium prediction in hepatectomy patients

OBJECTIVE

The objective of this study was to develop and validate a clinically applicable nomogram for predicting the risk of delirium following hepatectomy.

METHODS

We applied the LASSO regression model to identify the independent risk factors associated with POD. Subsequently, we utilized R software to develop and validate a nomogram model capable of accurately predicting the incidence of POD.

RESULTS

The final variables selected by the LASSO method were: Ramelteon, Age, Sex, Alcohol, Viral status, Cardiovascular disease, ASA class, Total bilirubin, Prothrombin time, Laparoscopic approach, and Blood transfusion. The performance of the nomogram was measured using ROC curve analysis, with an AUC of 0.854 (95% CI: 0.794-0.914) for the model. At the optimal cutoff value, the model demonstrated a sensitivity of 91.9% and a specificity of 68.8%. Model validation was performed using internal bootstrap validation to further verify the regression analysis. The ROC curve was generated by repeating the bootstrapping process 500 times, resulting in an AUC of 0.848 (95% CI: 0.786-0.904) for the model. The DCA curve representing the net benefit demonstrated the strong clinical validity of the model in predicting postoperative delirium.

CONCLUSION

Our results demonstrated that LASSO-based regression effectively constructed a nomogram model for predicting post-hepatectomy delirium.

A nomogram for postoperative pain relief in patients with osteoporotic vertebral compression fracture treated with polymethylmethacrylate bone cement

Osteoporotic vertebral compression fractures (OVCFs) can be painful. Percutaneous kyphoplasty (PKP) aims at strengthening the vertebra and reducing pain, but efficacy can vary among patients. The purpose of this study was to establish a risk prediction model for pain relief following PKP in patients with OVCF. This retrospective study included 208 (training set) and 54 (validation set) OVCF patients who underwent bone cement treatment between January 2018 and October 2023. Based on postoperative VAS scores, patients were divided into two groups (0-2 and 3-6). Univariable and multivariable logistic regression identified significant factors affecting VAS scores, leading to the creation of a nomogram model. Internal validation was performed using the bootstrap method. The model's performance and clinical value were evaluated using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and calibration curves. Four predictors were identified: number of segments, PMMA dose, comorbidities, and central nervous system (CNS) medications. The AUC, DCA, and calibration curves demonstrated good model discrimination and accuracy. The clinical impact plot highlighted the model's practical value. We developed and validated an intuitive nomogram model for predicting a postoperative VAS score ≤ 2, reflecting therapeutic efficacy in OVCF patients treated with PMMA. The model could be used for a more careful selection of patients suitable for PKP and who would benefit the most from PKP. The other patients should at least be advised of the risk of suboptimal pain control or directed toward other treatments.

Hip fractures in Spain. How are we? Systematic review and meta-analysis of the published registries

OBJECTIVE

Spain is expected to be the country with the highest life expectancy in the coming years. In this context, it is important to improve the care of hip fractures. The objective of this work was to describe the results of the registries published on hip fractures in Spain.

MATERIAL AND METHODS

Systematic review and meta-analysis of the records published on hip fractures in Spain, the last 10 years. The characteristics of the study, characteristics of the patients, of the fractures, the type of surgery, as well as morbidity and mortality were analyzed.

RESULTS

A total of 55,680 patients with a mean age of 84.6 years were analyzed, of whom 75% were women. Extracapsular fractures were the most frequent (58%). It was found that conservative treatment was applied in an average of 3% of cases. The average surgical delay was 64.7hours, with a mean percentage of patients operated on within 24hours at 18%, and within 48hours at 40%. A mean hospitalization time of 10.7 days was found. Delirium was found to be the most frequent postoperative complication (42%). The mean transfusion rate was 36%. Mean in-hospital mortality at one month and one year was 4%, 5% and 18%, respectively.

CONCLUSIONS

Less than half of patients with a hip fracture undergo surgery within 48hours, despite being recommended by the majority of clinical practice guidelines. Delirium is the most frequently reported postoperative complication, and one in every 5 patients will die within a year after a hip fracture. Standardizing the management of hip fractures at the state level could improve healthcare quality and facilitate the establishment of common criteria for good clinical practice.

A comprehensive predictive model for postoperative joint function in robot-assisted total hip arthroplasty patients: combining radiomics and clinical indicators

Total hip arthroplasty (THA) effectively treats various end-stage hip conditions, offering pain relief and improved joint function. However, surgical outcomes are influenced by multifaceted factors. This research aims to create a predictive model, incorporating radiomic and clinical information, to forecast post-surgery joint function in robot-assisted THA (RA-THA) patients. The study set comprised 136 patients who underwent unilateral RA-THA, which were subsequently partitioned into a training set (n = 95) and a test set (n = 41) for analysis. Preoperative CT imaging was employed to derive 851 radiomic characteristics, selecting those with an intra-class correlation coefficient > 0.75 for analysis. Least absolute shrinkage and selection operator regression reduced redundancy to six significant radiomic features. Clinical data including preoperative Visual Analog Scale (VAS), Harris Hip Score (HHS), and Western Ontario and McMaster University Osteoarthritis Index (WOMAC) score were collected. Logistic regression identified significant predictors, and three models were developed. Receiver operating characteristic and decision curves evaluated the models. Preoperative VAS, HHS, WOMAC score, and radiomics feature scores were significant predictors. In the training set, the AUCs were 0.835 (clinical model), 0.757 (radiomic model), and 0.891 (combined model). In the test set, the AUCs were 0.777 (clinical model), 0.824 (radiomic model), and 0.881 (combined model). The constructed nomogram prediction model combines radiological features with relevant clinical data to accurately predict functional outcomes 3 years after RA-THA. This model has significant prediction accuracy and broad clinical application prospects and can provide a valuable reference for formulating personalized treatment plans and optimizing patient management strategies.

Moderate to severe anemia at admission increases the risk of complications in patients over 60 years with hip fracture

BACKGROUND

Anemia frequently occurs in patients with hip fractures and represents a risk factor that can potentially be altered. To evaluate the association between admission anemia and complications in older hip fracture patients while exploring the potential impact of anemia on complications from the perspective of overall, operation and non-operation.

METHODS

This retrospective study enrolled in-patients over 60 years old with hip fractures from January 2020 to November 2023. At admission, anemic patients were identified as having a hemoglobin level below 12 g/dL in females and 13 g/dL in males. Anemia was further classified as mild, moderate, or severe. Data encompassing demographics, comorbidities, medications, information on fracture and surgery, and complications were collected.

RESULTS

A total of 462/679 patients had anemia, including 348, 105, and 9 with mild, moderate, and severe anemia, respectively. A total of 281 individuals experienced complications, including 212 and 69 with and without operation, respectively. Multivariate regression analysis identified anemia as a greater risk for acute heart failure (OR = 2.056, p = 0.037, 95% CI 1.043-4.052) than non-anemia. Moderate to severe anemia was a significant risk factor for any complication (OR = 1.584, p = 0.028, 95% CI 1.050-2.390), ≥ 2 (OR = 2.364, p = 0.001, 95% CI 1.443-3.872) or 3 (OR = 2.311, p = 0.022, 95% CI 1.131-4.720) complications, delirium (OR = 2.301, p = 0.018, 95% CI 1.156-4.579), venous thromboembolism (OR = 2.031, p = 0.042, 95% CI 1.025-4.025), and acute heart failure (OR = 2.095, p = 0.016, 95% CI 1.145-3.834), compared with mild to non-anemia. Similar results were observed in operated patients, while anemia and its severity were not associated with complications in non-operated patients.

CONCLUSION

Moderate to severe anemia caused complications in elderly hip fracture patients, but it was not observed in non-operated individuals. These findings would support orthopedic physicians' hierarchical management of anemic patients.

Risk factors and prediction model of delirium in elderly patients after hip arthroplasty

Objective

To analyze the risk factors of delirium in elderly patients after hip arthroplasty and to construct a prediction model.

Methods

Clinical data of 248 elderly patients who underwent hip arthroplasty in the Department of Traumatology and Orthopedics at Wuhan Fourth Hospital were retrospectively collected from November 2021 to February 2023. Logistic regression analysis was used to identify the risk factors of delirium after hip arthroplasty, and a nomogram prediction model was constructed using the RMS package of R4.1.2 software. The accuracy and stability of the model was evaluated based on the Hosmer-Lemeshow goodness-of-fit test and the receiver operating characteristic (ROC) curve.

Results

Age, nighttime sleep, anesthesia method, intraoperative blood loss, hypoxemia, and C-reactive protein (CRP) level were all risk factors of delirium after the hip arthroplasty (P<0.05). These factors were used to construct a nomogram prediction model that was internally validated using the Bootstrap method. The prediction model had the area under ROC curve (AUC) of 0.980 (95% CI: 0.964-0.996), indicating that it has certain predictive value for postoperative delirium. When the optimal cut off value was selected, the sensitivity and specificity were 92.7% and 92.3%, respectively, indicating that the prediction model is effective.

Conclusions

Age, short nighttime sleep, general anesthesia, high intraoperative blood loss, hypoxemia, and high CRP levels are independent risk factors for delirium after hip arthroplasty. The nomogram prediction model constructed based on these risk factors can effectively predict delirium in elderly patients after hip arthroplasty.

Predictive modeling for postoperative delirium in elderly patients with abdominal malignancies using synthetic minority oversampling technique

BACKGROUND

Postoperative delirium, particularly prevalent in elderly patients after abdominal cancer surgery, presents significant challenges in clinical management.

AIM

To develop a synthetic minority oversampling technique (SMOTE)-based model for predicting postoperative delirium in elderly abdominal cancer patients.

METHODS

In this retrospective cohort study, we analyzed data from 611 elderly patients who underwent abdominal malignant tumor surgery at our hospital between September 2020 and October 2022. The incidence of postoperative delirium was recorded for 7 d post-surgery. Patients were divided into delirium and non-delirium groups based on the occurrence of postoperative delirium or not. A multivariate logistic regression model was used to identify risk factors and develop a predictive model for postoperative delirium. The SMOTE technique was applied to enhance the model by oversampling the delirium cases. The model's predictive accuracy was then validated.

RESULTS

In our study involving 611 elderly patients with abdominal malignant tumors, multivariate logistic regression analysis identified significant risk factors for postoperative delirium. These included the Charlson comorbidity index, American Society of Anesthesiologists classification, history of cerebrovascular disease, surgical duration, perioperative blood transfusion, and postoperative pain score. The incidence rate of postoperative delirium in our study was 22.91%. The original predictive model (P1) exhibited an area under the receiver operating characteristic curve of 0.862. In comparison, the SMOTE-based logistic early warning model (P2), which utilized the SMOTE oversampling algorithm, showed a slightly lower but comparable area under the curve of 0.856, suggesting no significant difference in performance between the two predictive approaches.

CONCLUSION

This study confirms that the SMOTE-enhanced predictive model for postoperative delirium in elderly abdominal tumor patients shows performance equivalent to that of traditional methods, effectively addressing data imbalance.

The Nomogram Model and Factors for the Postoperative Mortality of Elderly Patients with Femoral Neck Fracture Undergoing Artificial Hip Arthroplasty: A Single-Institution 6-Year Experience

OBJECTIVE

Artificial hip arthroplasty (AHA) is widely accepted in elderly patients with femoral neck fractures, but it is associated with high risk of death and various postoperative complications due to old age and accompanying chronic diseases. Therefore, this study aimed to explore the risk factors for death in elderly patients with femoral neck fractures after AHA and to establish a nomogram risk prediction model, which is expected to reveal high-risk patients and improve the postoperative quality of life and survival rate of patients.

METHODS

Elderly patients who underwent AHA for femoral neck fractures in our hospital from September 2014 to May 2021were retrospectively analyzed. These patients were divided into a survival group and a death group according to their clinical outcomes. The following clinical data were recorded for the patients in the two groups: sex, age, underlying diseases, smoking and drinking history, preoperative nutritional risk score (NRS) and American Society of Anesthesiologists (ASA) score, as well as relevant indicators about the operation. These data were subject to univariate analysis and then logistic analysis to determine the risk factors of death. Subsequently, a nomogram risk prediction model was established and further validated with the receiver operating characteristic curve (ROC) and the Hosmer-Lemeshow test. Finally, the effects of predictive risk factors were analyzed using the Kaplan-Meier survival curve.

RESULTS

Follow-up was completed by 260 patients, including 206 patients in the survival group and 54 patients in the death group; the overall death rate was 20.77%, and the follow-up time, age, postoperative 1, 3 and 5-year death rates were 3.47 ± 1.93 years, 75.32 ± 9.12 years, 5.77%, 12.51%, and 25.61%, respectively. The top three causes of death in 54 patients were respiratory disease, cerebrocardiovascular disease, and digestive disease, respectively. The logistic analysis indicated that elderly patients with femoral neck fractures, the risk factors for death after AHA were age ≥ 80 years, preoperative NRS ≥ 4, HB ≤ 90 g/L, CR ≥ 110 umol/L, and ASA score ≥ 3, as well as postoperative albumin ≤ 35 g/L, the nomogram was established, and then its predictive performance was successfully validated using the ROC curve (AUC = 0.814, 95% confidence interval = 0.749-0.879) and the Hosmer-Lemeshow test (p = 0.840). Furthermore, Kaplan-Meier survival curve analysis revealed that the abovementioned six indicators were correlated with the post-AHA survival time of elderly patients with femoral neck fractures (pLog Rank  < 0.05).

CONCLUSION

Old age, preoperatively high NRS and ASA score, anemia, poor renal function, and postoperative hypoproteinemia are the major risk factors for death in elderly patients with femoral neck fractures after AHA; they are also associated with postoperative survival. Early identification and effective interventions for optimization of modifiable risk factors are recommended to improve the postoperative quality of life and survival rates.

Risk prediction models for postoperative delirium in elderly patients with fragility hip fracture: A systematic review and critical appraisal

BACKGROUND

Elderly patients with fragility hip fracture continue to experience a high rate of postoperative delirium (POD), which has a significant negative impact on prognosis and imposes a huge economic burden. A number of risk prediction models have been developed to detect POD early. However, the risk of bias and clinical applicability of the models remain unclear. The aim of this study was to systematically evaluate risk prediction models for POD.

METHODS

CNKI, WanFang DATA, Vip Database, SinoMed, PubMed, Web of Science, Embase, and the Cochrane Library were searched for studies published by July 2023. The literature was screened independently by two investigators. The Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) and the Prediction Model Risk of Bias Assessment Tool (PROBAST) were respectively used for data extraction, risk of bias, and applicability assessment.

RESULTS

A total of 16 studies on the construction of POD risk prediction models were included. The area under the ROC curve of the models ranges from 0.670 to 0.957. The most common predictors of POD included age, history of dementia, history of delirium, ASA classification, preoperative waiting time, and preoperative albumin level. All models had a high risk of bias, mainly due to inadequate sample size, inappropriate handling of missing data, a lack of model performance evaluation, and overfitting of the models.

CONCLUSIONS

Overall, risk prediction models for POD in fragility hip fracture patients are still in the development stage. The majority of POD prediction models have substantial bias risks, attributable primarily to poor reporting of analysis and evaluation of model performance. In future research, it is recommended to conduct validation of the models or develop localized prediction models with demonstrated high performance, with the aim of benefiting POD screening.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42023449153.

Incidence of delirium after non-cardiac surgery in the Chinese elderly population: a systematic review and meta-analysis

Background

POD places a heavy burden on the healthcare system as the number of elderly people undergoing surgery is increasing annually because of the aging population. As a large country with a severely aging population, China's elderly population has reached 267 million. There has been no summary analysis of the pooled incidence of POD in the elderly Chinese population.

Methods

Systematic search databases included PubMed, Web of Science, EMBASE, Cochrane Library Databases, China Knowledge Resource Integrated Database (CNKI), Chinese Biomedical Database (CBM), WanFang Database, and Chinese Science and Technology Periodicals (VIP). The retrieval time ranged from the database's establishment to February 8, 2023. The pooled incidence of delirium after non-cardiac surgery was calculated using a random effects model. Meta-regression, subgroup, and sensitivity analyses were used to explore the source of heterogeneity.

Results

A total of 52 studies met the inclusion criteria, involving 18,410 participants. The pooled incidence of delirium after non-cardiac surgery in the elderly Chinese population was 18.6% (95% CI: 16.4-20.8%). The meta-regression results revealed anesthesia method and year of publication as a source of heterogeneity. In the subgroup analysis, the gender subgroup revealed a POD incidence of 19.6% (95% CI: 16.9-22.3%) in males and 18.3% (95% CI: 15.7-20.9%) in females. The year of publication subgroup analysis revealed a POD incidence of 20.3% (95% CI: 17.4-23.3%) after 2018 and 14.6 (95% CI: 11.6-17.6%) in 2018 and before. In the subgroup of surgical types, the incidence of hip fracture surgery POD was 20.7% (95% CI: 17.6-24.3%), the incidence of non-cardiac surgery POD was 18.4% (95% CI: 11.8-25.1%), the incidence of orthopedic surgery POD was 16.6% (95% CI: 11.8-21.5%), the incidence of abdominal neoplasms surgery POD was 14.3% (95% CI: 7.6-21.1%); the incidence of abdominal surgery POD was 13.9% (95% CI: 6.4-21.4%). The anesthesia methods subgroup revealed a POD incidence of 21.5% (95% CI: 17.9-25.1%) for general anesthesia, 15.0% (95% CI: 10.6-19.3%) for intraspinal anesthesia, and 8.3% (95% CI: 10.6-19.3%) for regional anesthesia. The measurement tool subgroup revealed a POD incidence of 19.3% (95% CI: 16.7-21.9%) with CAM and 16.8% (95% CI: 12.6-21.0%) with DSM. The sample size subgroup revealed a POD incidence of 19.4% (95% CI: 16.8-22.1%) for patients ≤ 500 and 15.3% (95% CI: 11.0-19.7%) for patients > 500. The sensitivity analysis suggested that the pooled incidence of postoperative delirium in this study was stable.

Conclusion

Our systematic review of the incidence of delirium after non-cardiac surgery in elderly Chinese patients revealed a high incidence of postoperative delirium. Except for cardiac surgery, the incidence of postoperative delirium was higher for hip fracture surgery than for other types of surgery. However, this finding must be further explored in future large-sample studies.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier: PROSPERO CRD42023397883.