1.Analysis of demographic and clinical characteristics of 744 inpatients with osteoporotic vertebral compression fractures.
Bo ZHANG ; Wenlong MA ; Weihua FENG ; Yanjin WANG ; Hanjie ZHUO ; Yihang QIAO ; Haobo LIANG ; Zhenjie ZHAO
Chinese Journal of Reparative and Reconstructive Surgery 2025;39(3):354-361
OBJECTIVE:
To analyze the demographic and clinical characteristics of inpatients with osteoporotic vertebral compression fractures (OVCF) and provide a basis for clinical prevention and treatment.
METHODS:
A retrospective analysis was performed on the clinical data of 744 inpatients diagnosed with OVCF between January 2017 and December 2021 who met the inclusion criteria. Among them, 146 were male and 598 were female, with age ranging from 50 to 95 years (mean, 69.37 years). The demographic characteristics (gender, age, ethnicity, occupation, regional distribution, urban-rural distribution, and seasonal incidence) and clinical features [causes of injury, history of vertebral fractures, smoking and drinking history in males, comorbidities (hypertension, diabetes, coronary atherosclerotic heart disease, cerebral infarction), body mass index (BMI), blood lipid levels, menopausal age in females, vertebral bone mineral density T-value, number of vertebral fractures, and fracture segment distribution] of OVCF patients were analyzed. Multiple linear regression was used to analyze the independent risk factors of vertebral osteoporosis.
RESULTS:
The demographic analysis indicated that female patients with OVCF were significantly younger than male patients ( P<0.05). Significant differences were observed in the age distribution of OVCF between males and females ( P<0.05), with the highest proportion of male patients in the 70-79 years group (37.0%) and the highest proportion of female patients in the 60-69 years group (40.0%). From 2017 to 2021, the age of onset for OVCF gradually increased, with a similar trend observed for both genders. The distribution of occupations between genders also showed significant differences ( P<0.05); with the top three occupations for males being farmers (48.6%), retirees (24.7%), and workers (13.7%), while for females, the leading occupations were farmers (51.5%), retirees (19.4%), and service workers (10.0%). Female OVCF patients had higher BMI, vertebral bone mineral density T-value, history of vertebral fractures, hypertension prevalence, and blood lipid levels compared to male patients ( P<0.05). No significant difference between the males and the females was found in ethnicity, seasonal distribution, regional distribution, urban-rural distribution, causes of injury, number of vertebral fractures, or prevalence of comorbidities (except hypertension) ( P>0.05). Among the 744 OVCF patients, a total of 1 309 vertebrae were involved, with 628 thoracic vertebrae (48.0%) and 681 lumbar vertebrae (52.0%). The most common fracture segments were L 1 (22.5%), T 12 (21.2%), followed by L 2 (12.2%) and T 11 (10.2%). No significant gender difference was observed in the distribution of fracture segments ( P>0.05). Multiple linear regression analysis indicated that older age, female, and lower BMI were independent risk factors for vertebral osteoporosis ( P<0.05).
CONCLUSION
The age of onset of OVCF patients is increasing year by year. The number of fractured vertebral bodies, age distribution of morbidity, occupational distribution, BMI, history of vertebral fracture, hypertension, and blood lipid levels are related to gender. The occurrence of OVCF is mainly in the thoracolumbar segment. The female, older age, and lower BMI are independent risk factors of osteoporosis.
Humans
;
Male
;
Female
;
Aged
;
Middle Aged
;
Retrospective Studies
;
Spinal Fractures/etiology*
;
Aged, 80 and over
;
Osteoporotic Fractures/etiology*
;
Fractures, Compression/etiology*
;
Risk Factors
;
Bone Density
;
China/epidemiology*
;
Osteoporosis/epidemiology*
;
Comorbidity
;
Inpatients
;
Sex Factors
;
Age Factors
2.Correlation between bone mass loss and incidence of knee osteoarthritis in the elderly community-based population.
Chen-Jie XIA ; Jin LI ; Xiang LI ; Ke ZHOU ; Liang FANG ; Hong-Ting JIN ; Pei-Jian TONG
China Journal of Orthopaedics and Traumatology 2025;38(4):358-363
OBJECTIVE:
To explore the epidemiological characteristics of knee osteoarthritis (KOA) among the elderly in the community, and its correlation with bone mass loss.
METHODS:
A cross-sectional study was conducted on elderly community population over 50 year old from 12 community health service centers in Zhejiang province. Their gender, age, body mass index (BMI), T value and KOA diagnosis were collected using face to face questionnaire survey. Univariate regression was used to analyze the influence of age, gender, BMI and bone loss on KOA. Logistic multivariate regression model was used to analyze the independent effect of bone mass loss on KOA.
RESULTS:
Among 4 173 subjects in this study, 1 710 of them were had a KOA. The prevalence rate was 40.9%. The mean age, the proportion of females and the mean BMI in KOA patients were (65.5±3.8) years old, 67.7%(1 158/1 710) and(24.59±1.28) kg·m-2, respectively, which were significantly higher than (58.5±3.2) years old, 51.3%(1 263/2 463), and (23.48±1.25) kg·m-2 in non-KOA subjects (P<0.001). In the population aged from 60 to 69 years old, the influence of osteopenia and osteoporosis on the prevalence of KOA was[OR=1.21, 95%CI(1.00, 1.46), P=0.053 2], [OR=1.42, 95%CI(1.14, 1.78), P=0.002 2]. The influence of male and female osteoporosis on the prevalence of KOA was [OR=1.52, 95%CI(1.16, 1.99), P=0.002 7] and [OR=1.87, 95%CI(1.51, 2.32), P<0.000 1], respectively. In the population of 24 kg·m-2≤BMI<28 kg·m-2, the influence of osteopenia and osteoporosis on the prevalence of KOA was [OR=1.47, 95%CI(1.21, 1.80), P=0.000 1], [OR=2.69, 95%CI(2.11, 3.42), P<0.000 1], respectively. After controlling the confounding factors of age, gender and BMI, compared with people with normal bone mass, the effect of osteopenia on the prevalence of KOA was [OR=1.34, 95%CI(1.08, 1.67), P=0.009 2], and the effect of osteoporosis on the prevalence of KOA was [OR=1.38, 95%CI(1.06, 1.79), P=0.017 9].
CONCLUSION
Elderly overweight women are more likely to develop KOA. Bone mass loss is an independent risk factor for KOA, which will significantly increase the prevalence of KOA in people overweight or aged 60 to 69 years old.
Humans
;
Female
;
Male
;
Aged
;
Osteoarthritis, Knee/etiology*
;
Middle Aged
;
Cross-Sectional Studies
;
Bone Density
;
Aged, 80 and over
;
Incidence
;
Body Mass Index
;
China/epidemiology*
;
Osteoporosis/epidemiology*
3.Bone loss in patients with spinal cord injury: Incidence and influencing factors.
Min JIANG ; Jun-Wei ZHANG ; He-Hu TANG ; Yu-Fei MENG ; Zhen-Rong ZHANG ; Fang-Yong WANG ; Jin-Zhu BAI ; Shu-Jia LIU ; Zhen LYU ; Shi-Zheng CHEN ; Jie-Sheng LIU ; Jia-Xin FU
Chinese Journal of Traumatology 2025;28(6):477-484
PURPOSE:
To investigate the incidence and influencing factors of bone loss in patients with spinal cord injury (SCI).
METHODS:
A retrospective case-control study was conducted. Patients with SCI in our hospital from January 2019 to March 2023 were collected. According to the correlation between bone mineral density (BMD) at different sites, the patients were divided into the lumbar spine group and the hip joint group. According to the BMD value, the patients were divided into the normal bone mass group (t > -1.0 standard deviation) and the osteopenia group (t ≤ -1.0 standard deviation). The influencing factors accumulated as follows: gender, age, height, weight, cause of injury, injury segment, injury degree, time after injury, start time of rehabilitation, motor score, sensory score, spasticity, serum value of alkaline phosphatase, calcium, and phosphorus. The trend chart was drawn and the influencing factors were analyzed. SPSS 26.0 was used for statistical analysis. Correlation analysis was used to test the correlation between the BMD values of the lumbar spine and bilateral hips. Binary logistic regression analysis was used to explore the influencing factors of osteoporosis after SCI. p < 0.05 was considered statistically significant.
RESULTS:
The incidence of bone loss in patients with SCI was 66.3%. There was a low concordance between bone loss in the lumbar spine and the hip, and the hip was particularly susceptible to bone loss after SCI, with an upward trend in incidence (36% - 82%). In this study, patients with SCI were divided into the lumbar spine group (n = 100) and the hip group (n = 185) according to the BMD values of different sites. Then, the lumbar spine group was divided into the normal bone mass group (n = 53) and the osteopenia group (n = 47); the hip joint group was divided into the normal bone mass group (n = 83) and the osteopenia group (n = 102). Of these, lumbar bone loss after SCI is correlated with gender and weight (p = 0.032 and < 0.001, respectively), and hip bone loss is correlated with gender, height, weight, and time since injury (p < 0.001, p = 0.015, 0.009, and 0.012, respectively).
CONCLUSIONS
The incidence of bone loss after SCI was high, especially in the hip. The incidence and influencing factors of bone loss in the lumbar spine and hip were different. Patients with SCI who are male, low height, lightweight, and long time after injury were more likely to have bone loss.
Humans
;
Spinal Cord Injuries/complications*
;
Male
;
Female
;
Retrospective Studies
;
Incidence
;
Adult
;
Bone Density
;
Middle Aged
;
Case-Control Studies
;
Osteoporosis/etiology*
;
Lumbar Vertebrae
;
Bone Diseases, Metabolic/etiology*
;
Aged
;
Risk Factors
4.Bisphosphonates-related osteonecrosis of the jaw: A case report.
Ju YANG ; Yue LIU ; Chunna QU ; Jianbin SUN ; Tianying LI ; Lianjie SHI
Journal of Peking University(Health Sciences) 2025;57(2):388-392
Osteonecrosis of the mandible is also called avascular necrosis of the jaw, and it is a rare complication of bisphosphonates. It is characterized with pain, swelling, exposure of bone, local infection and pathologic fractures of the jaw. With the widespread usage of bisphosphonates in bone metastasis of malignant tumors and osteoporosis, this rare complication has received more attention in recent years. Here, we reported a case of bisphosphonates-related osteonecrosis of the jaw (BRONJ) caused by intravenous zoledronic acid for osteoporosis. A 62-year-old female patient with 7-year history of Sjögren's syndrome and 3-year history of osteoporosis developed BRONJ after 3-year treatment of zoledronic acid. Two months before she went to the Peking University International Hospital, she visited the dentist for periodontal purulent secretion and extracted one tooth from the right mandible. However, the condition was not improved and she felt persistent pain and swelling in the right mandible. Hence, she received repeated root curettage, but there was no improvement. Finally, she was diagnosed with osteonecrosis of the mandible based on the digital volume tomography scan, which showed right mandibular osteonecrosis bone destruction. She underwent surgical debridement of the necrotic bone and administered intravenous antibio-tics at the Peking University International Hospital. Histopathological analysis of the bone biopsy further confirmed the diagnosis of BRONJ. Her condition was improved successfully during a 3-year follow-up. Osteonecrosis of the mandible become more common with the increased use of bisphosphonates. Recent study has reported that osteonecrosis of the mandible is more likely to occur in patients with Sjögren's syndrome. In addition, age, long-term and irregular administration of glucocorticoids, irregular oral examination and treatment also might be the risk factors in the pathogenesis of osteonecrosis of the mandible. For the elder osteoporosis patients who would receive or had received bisphosphonate-related drugs, oral health status and the disease states associated with necrosis of the mandible such as Sjögren's syndrome should be comprehensively measured and fully evaluated during the whole process. Furthermore, to better understand and prevent or reduce the occurrence of this complication, we reviewed the patho-genesis, diagnosis, treatment, and prevention of BRONJ.
Humans
;
Female
;
Middle Aged
;
Bisphosphonate-Associated Osteonecrosis of the Jaw/etiology*
;
Diphosphonates/administration & dosage*
;
Zoledronic Acid
;
Imidazoles/administration & dosage*
;
Bone Density Conservation Agents/adverse effects*
;
Osteoporosis/drug therapy*
5.An Investigation of the Association between Metabolic Syndrome and Osteoporosis Based on Chinese Health Examination Data.
Hongyu CHEN ; Mingyang ZHENG ; Qingli CHENG ; Jiahui ZHAO ; Yansong ZHENG
Biomedical and Environmental Sciences 2024;37(12):1385-1396
OBJECTIVE:
Because of the limited number of studies and small sample sizes, whether metabolic syndrome (MS) leads to the occurrence and progression of osteoporosis and the possible underlying mechanisms require further investigation. This study aimed to investigate the association between MS and osteoporosis, along with its influencing factors.
METHODS:
This observational cross-sectional study included 139,470 individuals aged ≥ 18 years who underwent health examinations from September 2014 to March 2022. Based on bone mineral density (BMD) screening results, the participants were categorized into a suspected osteoporosis or non-osteoporosis group (control). Participants were further divided into those who met 0 MS criteria, 1 MS criterion, 2 MS criteria, and ≥ 3 MS criteria (MS group). Participants who had undergone health examinations at least twice formed the follow-up cohort; a self-matched analysis was performed on those with follow-up periods ≥ 5 years and unchanged MS grouping.
RESULTS:
Several examination indicators in the suspected osteoporosis group showed statistically significant differences compared with the control group. The proportion of suspected osteoporosis in the MS group was significantly increased compared with that in the 0 MS criteria group (odds ratio [ OR]: 1.215, Z = 29.11, P < 0.001, 95% confidence interval: 1.199-1.231). After adjusting for age, sex, smoking, and alcohol consumption, the 2 MS criteria group and MS group still had OR values > 1 ( P < 0.001). In the follow-up cohort, the proportion of suspected osteoporosis increased gradually with an increase in the number of MS criteria met at baseline and during each follow-up visit ( P < 0.05), with the highest proportion observed in the MS group. However, the proportion of suspected osteoporosis did not increase significantly over time in the different MS groups ( P > 0.05). In the follow-up cohort, the proportion of individuals transitioning from normal BMD to suspected osteoporosis was higher in the MS group after ≥ 5 years of follow-up compared with the group meeting 0 MS criteria (0.08% versus 1.15%, χ 2 = 10.76, P = 0.001). There was no significant difference in BMD values for the 0 MS criteria group after 5 years ( P > 0.05), whereas the other three groups experienced a significant decrease in BMD values after 5 years ( P < 0.05).
CONCLUSION
MS is an independent risk factor for osteoporosis, and the effect of risk factors related to MS on osteoporosis may exceed that of aging alone. The specific mechanisms warrant further investigation.
Humans
;
Osteoporosis/etiology*
;
Female
;
Male
;
Metabolic Syndrome/complications*
;
Middle Aged
;
Cross-Sectional Studies
;
China/epidemiology*
;
Aged
;
Adult
;
Bone Density
;
Risk Factors
6.Study on correlation between bone marrow edema and osteoporosis in patients with severe knee osteoarthritis.
Long-Wen XIAO ; Zhi-Cheng SANG
China Journal of Orthopaedics and Traumatology 2023;36(4):371-375
OBJECTIVE:
To explore relationship between bone marrow edema(BME) and osteoporosis in patients with severe knee osteoarthritis.
METHODS:
Unmatched case-control study was conducted. Totally 160 patients with severe knee osteoarthritis who had undergone knee magnetic resonance imaging (MRI) and bone mineral density examination (BMD) from January 2020 to March 2021 were included. Eighty patients complicated with BME were included in BME group, and 80 patients without BME were selected as NBME group. In BME group, there were 12 males and 68 females, aged from 51 to 80 years old with an average of(66.58±8.10) years old;the courses of disease ranged from 5 to 40 months with an average of (15.61±9.25) months;body mass index(BMI) ranged from 21.81 to 34.70 with an average of (27.79±3.00) kg·m-2;25 patients classified to grade Ⅲ and 55 patients grade Ⅳ according to Kellgren- Lawrence(K-L). In NBME group, there were 15 males and 65 females, aged from 50 to 80 years old with an average of(67.82±8.05) years old;the course of disease ranged from 6 to 37 months with an average of(15.75±8.18) months;BMI ranged from 21.39 to 34.46 with an average of (28.26±3.13) kg·m-2;25 patients were K-L Ⅲ and 55 patients with K-L Ⅳ. The degree of bone marrow edema was evaluated by knee whole oragan magnetic resonance imaging score(WORMS). Osteoporosis was diagnosed and BMD was evaluated by DXA T value. To explore the relationship between bone marrow edema and osteoporosis by comparing prevalence rate of osteoporosis between two groups, and to further explore relationship between BME and BMD by Spearman correlation analysis of BME WORMS score and DXA T value in BME group.
RESULTS:
The complete case data were obtained on the first diagnosis, and there was no significant difference in sex, age, courses of disease and BMI between two groups (P>0.05). The proportion of K-L Ⅳ in BME group was significantly higher than that in NBME (P<0.05). The prevalence rate of osteoporosis in BME group was significantly higher than in NBME group with the same K-L grade (P<0.001), and there was a strong negative correlation between BME WORMS score and DXA BMD T value (r=-0.812, |r|=0.812 >0.8, P<0.001).
CONCLUSION
Osteoporosis is one of the risk factors of bone marrow edema in patients with severe knee osteoarthritis, and the lower the bone mineral density is, the easier it is to be complicated with bone marrow edema.
Male
;
Female
;
Humans
;
Osteoarthritis, Knee/diagnostic imaging*
;
Bone Marrow/pathology*
;
Case-Control Studies
;
Bone Marrow Diseases/etiology*
;
Osteoporosis/complications*
;
Edema/etiology*
;
Magnetic Resonance Imaging/methods*
7.Telecarers improve osteoporosis treatment and compliance rates in secondary osteoporosis prevention for elderly hip fracture patients.
Linsey Utami GANI ; Francine Chiu Lan TAN ; Thomas Federick James KING
Singapore medical journal 2023;64(4):244-248
INTRODUCTION:
A significant treatment gap has been observed in patients with osteoporosis. Our previous audit found a 31.5% rate of anti-osteoporosis medication initiation after fragility fractures at one year. We piloted the use of telecarers to monitor osteoporosis treatment and compliance.
METHODS:
From January 2017 to January 2018, all hip fracture patients at Changi General Hospital, Singapore, were automatically enrolled into the Health Management Unit valued care hip fracture programme. Telecarer calls were scheduled at discharge, 3, 6 and 12 months. We assessed the acceptability, completion and treatment rates of patients enrolled in this programme.
RESULTS:
A total of 537 patients with a hip fracture were enrolled in the telecarer programme over one year. Their average age was 79.8 ± 8.23 years, and 63.1% of them were female. A total of 341 patients completed 12 months of follow-up, of which 251 (73.6%) patients were on treatment at 12 months. The most common cause of lack of initiation of secondary osteoporosis treatment was patient or family rejection (34.4%), followed by physician failure to prescribe (24.4%) and renal impairment (24.4%). 16.7% of patients were deemed to have advanced dementia with a life-limiting illness and were, thus, deemed unsuitable for treatment.
CONCLUSION
Telecarers may be a useful adjunct in the monitoring of osteoporosis treatment after hip fractures in an elderly population. The main limitations are patient or family rejection and physician inertia. Further studies should focus on a combination of interventions for both patients and physicians to increase awareness of secondary fracture prevention.
Humans
;
Female
;
Aged
;
Aged, 80 and over
;
Male
;
Osteoporotic Fractures/drug therapy*
;
Bone Density Conservation Agents/therapeutic use*
;
Osteoporosis/drug therapy*
;
Hip Fractures/etiology*
;
Secondary Prevention
8.Risk factors of hidden blood loss in percutaneous vertebral augmentation.
Zhi-Hua WU ; Ling MO ; Huan-Tong CHENG ; De LIANG ; Jian-Chao CUI ; Jing-Jing TANG ; Hui REN ; Zhen-Song YAO ; Xiao-Bing JIANG
China Journal of Orthopaedics and Traumatology 2022;35(8):732-735
OBJECTIVE:
To explore the risk factors of hidden blood loss in osteoporosis vertebral compression fractures during percutaneous vertebral augmentation.
METHODS:
From October 2018 to December 2019, 360 patients with osteoporosis vertebral compression fractures who received percutaneous vertebral augmentation were enrolled in this study. The factors analyzed included gender, age, surgical methods, disease course, height, weight, the operative segment, bone mineral density, amount of bone cement, operative time, percentage of height loss, percentage of vertebral height restoration, cement leakage, blood clotting function, preoperative and postoperative hemoglobin and hematocrit and other internal diseases. Total blood loss was calculated by Gross's formula, influential factors of the hidden blood loss were further analyzed by t-test, multivariate linear regression and one-way ANOVA analysis.
RESULTS:
Surgical methods, the operative segment, disease course, cement leakage, preoperative hemoglobin, cement leakage via the basivertebral and segmental vein were significantly correlated with hidden blood loss(P<0.05).
CONCLUSION
Patients with percutaneous kyphoplasty, two-level and multi-level surgery, the course of the disease beyond 6 weeks, cement leakage via the basivertebral and segmental vein, and lower preoperative hemoglobin had more perioperative hidden blood loss.
Bone Cements/adverse effects*
;
Fractures, Compression/etiology*
;
Humans
;
Kyphoplasty/methods*
;
Osteoporosis/complications*
;
Osteoporotic Fractures/surgery*
;
Retrospective Studies
;
Risk Factors
;
Spinal Fractures/etiology*
;
Treatment Outcome
;
Vertebroplasty/adverse effects*
9.Prevalence of osteoporosis and related factors in postmenopausal women aged 40 and above in China.
Shu Nyu TANG ; Xiang Jun YIN ; Wei YU ; Lu CUI ; Zhi Xin LI ; Li Jia CUI ; Lin Hong WANG ; Wei Bo XIA
Chinese Journal of Epidemiology 2022;43(4):509-516
Objective: To understand the prevalence of osteoporosis and related factors in postmenopausal women aged ≥40 years in China and provide scientific evidence for osteoporosis prevention and control. Methods: Data of this study were from the 2018 China Osteoporosis Epidemiological Survey, covering 44 counties (districts) in 11 provinces in China. Related variables were collected by questionnaire survey and physical measurement, and the BMD of lumbar spine and proximal femur was measured by dual-energy X-ray absorption method. The prevalence of osteoporosis and its 95%CI in postmenopausal women aged ≥40 years were estimated with complex sampling weights. Results: A total of 5 728 postmenopausal women aged ≥40 years were included in the analysis and the prevalence of osteoporosis was 32.5% (95%CI: 30.3%-34.7%). The prevalence of osteoporosis in postmenopausal women aged 40-49 years, 50-59 years, 60-69 years, 70-79 years, and ≥80 years were 16.0% (95%CI:4.5%-27.5%), 18.4% (95%CI:15.9%-20.8%), 37.5% (95%CI:34.5%-40.4%), 52.9% (95%CI: 47.5%-58.3%), and 68.0% (95%CI:55.9%-80.1%) respectively. The prevalence of osteoporosis was higher (P<0.001) in those with education level of primary school or below (47.2%, 95%CI: 43.0%-51.3%) and in those with individual annual income less than 10 000 Yuan, (40.3%, 95%CI: 36.9%-43.7%). The prevalence of osteoporosis was 35.1% in rural areas (95%CI: 32.0%-38.1%), which was higher than that in urban areas (P<0.001). The prevalence of osteoporosis in low weight, normal weight, overweight and obese groups were 69.9% (95%CI: 59.0%-80.8%), 42.2% (95%CI: 38.7%-45.7%), 24.2% (95%CI: 21.3%-27.1%) and 14.6% (95%CI: 11.1%-18.0%), respectively. The prevalence of osteoporosis in those with menstrual maintenance years ≤30 years and in those with menopause years ≥11 years were 46.1% (95%CI:40.8%-51.3%) and 48.2% (95%CI:45.0%-51.3%), respectively. Multivariate logistic analysis showed that age ≥60 years, education level of primary school or below, annual household income per capita less than 10 000 Yuan, low body weight, menstrual maintenance years ≤30 years, menopause years ≥11 years were risk factors of osteoporosis in postmenopausal women in China. Conclusions: The prevalence of osteoporosis was high in postmenopausal women aged ≥40 years in China, and there were differences in osteoporosis prevalence among different socioeconomic groups. Effective interventions should be taken for the prevention and control of osteoporosis in key groups in the future.
Absorptiometry, Photon
;
Bone Density
;
China/epidemiology*
;
Female
;
Humans
;
Lumbar Vertebrae
;
Osteoporosis/epidemiology*
;
Osteoporosis, Postmenopausal/etiology*
;
Postmenopause
;
Prevalence
;
Risk Factors
10.Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis.
Yaxin CHEN ; Tianyi YANG ; Xiaofeng GAO ; Ajing XU
Frontiers of Medicine 2022;16(3):496-506
The fracture risk of patients with diabetes is higher than those of patients without diabetes due to hyperglycemia, usage of diabetes drugs, changes in insulin levels, and excretion, and this risk begins as early as adolescence. Many factors including demographic data (such as age, height, weight, and gender), medical history (such as smoking, drinking, and menopause), and examination (such as bone mineral density, blood routine, and urine routine) may be related to bone metabolism in patients with diabetes. However, most of the existing methods are qualitative assessments and do not consider the interactions of the physiological factors of humans. In addition, the fracture risk of patients with diabetes and osteoporosis has not been further studied previously. In this paper, a hybrid model combining XGBoost with deep neural network is used to predict the fracture risk of patients with diabetes and osteoporosis, and investigate the effect of patients' physiological factors on fracture risk. A total of 147 raw input features are considered in our model. The presented model is compared with several benchmarks based on various metrics to prove its effectiveness. Moreover, the top 18 influencing factors of fracture risks of patients with diabetes are determined.
Bone Density
;
Deep Learning
;
Diabetes Mellitus/epidemiology*
;
Female
;
Fractures, Bone/etiology*
;
Humans
;
Osteoporosis/complications*
;
Risk Factors

Result Analysis
Print
Save
E-mail