Machine learning applications for the prediction of extended length of stay in geriatric hip fracture patients

BACKGROUND

Geriatric hip fractures are one of the most common fractures in elderly individuals, and prolonged hospital stays increase the risk of death and complications. Machine learning (ML) has become prevalent in clinical data processing and predictive models. This study aims to develop ML models for predicting extended length of stay (eLOS) among geriatric patients with hip fractures and to identify the associated risk factors.

AIM

To develop ML models for predicting the eLOS among geriatric patients with hip fractures, identify associated risk factors, and compare the performance of each model.

METHODS

A retrospective study was conducted at a single orthopaedic trauma centre, enrolling all patients who underwent hip fracture surgery between January 2018 and December 2022. The study collected various patient characteristics, encompassing demographic data, general health status, injury-related data, laboratory examinations, surgery-related data, and length of stay. Features that exhibited significant differences in univariate analysis were integrated into the ML model establishment and subsequently cross-verified. The study compared the performance of the ML models and determined the risk factors for eLOS.

RESULTS

The study included 763 patients, with 380 experiencing eLOS. Among the models, the decision tree, random forest, and extreme Gradient Boosting models demonstrated the most robust performance. Notably, the artificial neural network model also exhibited impressive results. After cross-validation, the support vector machine and logistic regression models demonstrated superior performance. Predictors for eLOS included delayed surgery, D-dimer level, American Society of Anaesthesiologists (ASA) classification, type of surgery, and sex.

CONCLUSION

ML proved to be highly accurate in predicting the eLOS for geriatric patients with hip fractures. The identified key risk factors were delayed surgery, D-dimer level, ASA classification, type of surgery, and sex. This valuable information can aid clinicians in allocating resources more efficiently to meet patient demand effectively.

Relationships among body weight, lipids and bone mass in elderly individuals with fractures: A case-control study

BACKGROUND

The prevalence of osteoporosis and low bone mass is steadily rising each year. Low body weight is commonly linked to diminished bone mass and serves as a robust predictor of osteoporosis. Nonetheless, the connection between body mass index (BMI), bone mineral density, and lipid profiles among the elderly remains elusive.

AIM

To examine the association between BMI and bone mass, explore the correlation between lipid profiles and bone mass, and delve into the interplay between lipid metabolism and bone health.

METHODS

The study included 520 patients aged ≥ 65 years (178 men and 342 women). Age, sex, weight, and height were recorded. Femoral neck bone mineral density and T scores were determined using a dual-energy X-ray absorptiometry scanner. Blood calcium (Ca), phosphorus (P), albumin (ALB), alkaline phosphatase (ALP), aspartate aminotransferase, alanine aminotransferase, triglyceride (TG), total cholesterol (TC), high-density lipoprotein (HDL) and low-density lipoprotein (LDL) levels were measured. Patients were classified by sex (male and female), age (65-79 years and ≥ 80 years), and T score (normal bone mineral density, osteopenia and osteoporosis).

RESULTS

Age, sex, BMI, and ALP and TG levels were independent risk factors for osteoporosis. For the 65-79- and ≥ 80-year-old groups, females presented lower T scores than males. Ca, P, ALB, ALP, TC, HDL and LDL levels were significantly different between men and women in the 65-79-year-old group. In addition, BMI and TG levels were significantly decreased in osteoporotic patients compared with patients with normal bone mass. TC levels declined in 65- to 79-year-old male and female osteoporosis patients. In the group of women aged ≥ 80 years, osteoporotic patients showed significantly increased ALP levels. Furthermore, we found positive correlations between BMI and TG levels in the male and female patient groups. However, we found no significant differences in ALB, Ca, P, HDL and LDL levels in osteoporotic patients compared to patients with normal bone mass.

CONCLUSION

Osteoporotic patients showed significantly decreased BMI and TG levels compared with those with normal bone mass. BMI showed positive correlations with TG levels in male and female patients. These results indicate correlations between BMI and bone mass and between lipid profiles and bone mass.

[Effect of Friday surgery on clinical outcome of elderly patients with hip fracture under multidisciplinary treatment]

Objective: To assess the impact of Friday surgery on clinical outcomes in elderly patients with hip fracture under multidisciplinary treatment. Methods: A retrospective cohort study. The clinical data of 414 geriatric patients with hip fractures admitted to Zhongda Hospital Affiliated with Southeast University from January 2018 to March 2021 were analyzed retrospectively, including 126 males and 288 females with a mean age of (81.3±7.6) years. The patients were divided into two groups based on whether they underwent surgery on Friday or not. The Friday group(n=69) and the non-Friday group(n=345) were compared in terms of general information, American Society of Anesthesiologists(ASA) classification, fracture type, injury to admission time, preoperative waiting time, surgical method, anesthesia type and use of intensive care unit (ICU) fast track. Propensity score matching (PSM) was performed based on age, ASA grade, time from injury to admission, preoperative waiting time, hemoglobin and albumin levels at admission. Clinical outcomes were collected and compared between the two groups, including length of hospital stay, total hospitalization cost and 30-day, 90-day and 1-year mortality rates, and postoperative complications. Multivariate logistic regression analyses were conducted to identify influencing factors for 1-year mortality in geriatric patients with hip fracture. Results: Baseline data showed statistically significant differences in hemoglobin, albumin and preoperative waiting time between the two groups (all P<0.05). After PSM matching, 69 patients were included in each group, and no significant differences were observed in baseline data between the two groups (all P>0.05). There was no significant differences in 30-day mortality rate (4.3% vs 0, P=0.080), 90-day mortality rate (7.2% vs 1.4%, P=0.095), length of hospital stay [(10.85±4.45)d vs (10.92±3.68)d, P=0.919], total hospitalization cost [(60.9±15.4) thousands yuan vs (59.1±15.4) thousands yuan, P=0.489], postoperative complications [pneumonia (11.6% vs 13.0%, P=0.796), cardio-cerebrovascular complications (11.6% vs 8.7%, P=0.573) and delirium (5.7% vs 2.9%, P=0.245)] between the Friday group and the non-Friday group (all P>0.05). However, the 1-year mortality rate was higher in the Friday group than that in the non-Friday group(18.8% vs 4.3%, P=0.008). Multivariate analysis revealed that surgery on Friday (OR=11.222, 95%CI: 2.198-57.291, P=0.004), low hemoglobin levels at admission (OR=0.920, 95%CI: 0.875-0.967, P=0.001), hemiarthroplasty treatment (OR=5.127, 95%CI: 1.308-20.095, P=0.019) and longer surgery duration (OR=0.958, 95%CI: 0.927-0.989, P=0.009) were influencing factors for 1-year mortality in geriatric patients with hip fracture. Conclusions: In the context of multidisciplinary treatment, Friday surgery does not increase short-term mortality, length of hospital stay, total hospitalization cost or incidence of complications in geriatric patients with hip fracture. However, it remains a influencing factor for 1-year mortality in those patients.

[Application and thinking of health standards related to medical care and health information in prevention and control of COVID-19]

Objective: To compare the technical elements of health standards for nosocomial infection control, health protection, health information, and health emergency and biosafety in the context of the prevention and control of COVID-19, and provide support for the further optimization of the epidemic prevention and control guidelines. Methods: Above mentioned health standards used in COVID-19 prevention and control were collected for a systematic comparison with "Guidelines for Prevention and Control of COVID-19 in Medical Institutions" (the 1(st) Edition) from the perspective of technical elements. Results: The application scope and technical elements of the current health standards basically meet the needs for the prevention and control of COVID-19 epidemic. Conclusions: The implementation of the current health standards can provide strong technical support for the prevention and control of COVID-19 epidemic. The experience obtained in the epidemic prevention and control can also contribute to the further revision and improvement of the health standards.

Wavelength modulation technique-based photoacoustic spectroscopy for multipoint gas sensing

A multipoint gas sensing scheme based on photoacoustic spectroscopy was proposed. Multiple photoacoustic spectroscopy (PAS) gas cells (resonant frequency f₀=5.0  kHz) were connected in series for the multipoint gas sensing with wavelength modulation technique. The PAS signal was excited by modulating the tunable distributed feedback laser diode wavelength at f₀/2 using a changing driving current. The gas concentration of each gas cell was obtained by the PAS signal, which was demodulated by the lock-in amplifier. A multipoint PAS experiment to detect the water vapor at 1368.597 nm was implemented to verify the scheme we presented. With the three PAS gas cells, the linear response to the water vapor concentration of our sensors achieved 0.9978, 0.99591, and 0.99617, and their minimum detection limits were 479, 662, and 630 ppb, respectively.