Psychometric properties of the Spanish version of the Chalder Fatigue Scale in clinical and general populations / Propiedades psicométricas de la versión española de la Escala de Fatiga de Chalder en población clínica y general

Objetivo: La Escala de Fatiga de Chalder (CFS) es una escala breve para evaluar fatiga que se utiliza en España, pero que no ha sido validada en su población. El objetivo del estudio fue adaptar y evaluar las propiedades psicométricas de la versión española de la CFS (Sp-CFS). Método: La muestra la conformaron 3,671 participantes (3.190 de la población general y 481 pacientes), con edades entre 18 y 86 años (M = 28.43; DT = 12.71), siendo el 67.6% mujeres. Las propiedades psicométricas de la escala se probaron en un diseño transversal utilizando validación cruzada (análisis factorial exploratorio y confirmatorio) y estimación de la invarianza (sexo y condición clínica). Resultados: Un modelo de cuatro factores (baja energía, problemas de sueño, problemas de concentración y disfunción cognitiva subjetiva) en lugar de un modelo original de dos factores (fatiga física y mental) proporcionó mejores índices de bondad de ajuste a los datos. La consistencia interna y la estabilidad de la escala fueron excelentes. Su validez convergente se apoyó en su asociación significativa con la ansiedad, la depresión, el estrés y los síntomas positivos y negativos del espectro de la psicosis. El instrumento no mostró diferencias significativas entre sexos ni condiciones clínicas, y discriminó entre la población general y los pacientes, obteniendo estos últimos puntajes significativamente mayores. Conclusiones: Sp-CFS es una escala fiable y válida para medir la fatiga en población general y clínica española.(AU)

Objective:The Chalder Fatigue Scale (CFS) is a brief self-report screening scale for fatigue that is used in Spain but has not been validated for the Spanish population. The aim of this study was to adapt and evalu-ate the psychometric properties of the Spanish version of the CFS (Sp-CFS). Method:The sample consisted of 3,671 participants (3,190 from the general population and 481 patients), aged 18 to 86 years (M=28.43; DT=12.71), 67.6% of whom were women. Psychometric properties of the scale were tested in a cross-sectional design using cross-validation (explora-tory and confirmatory factor analysis) and estimation of invariance (sex and clinical condition). Results:A four-factor model (low energy, sleep problems, concentration problems and subjective cognitive dysfunction) rather than an original two-factor model (physical and mental fatigue) pro-vided better indices of goodness of fit to the data. The internal consistencyand stability of the scale were excellent. Its convergent validity was sup-ported by its significant association with anxiety, depression, stress, and the positive and negative symptoms of the psychosis spectrum. The instru-ment did not show significant differences between sexes or clinical condi-tions, and it discriminated between the general population and the patients, with the latter obtaining significantly greater scores. Conclusions: Sp-CFS is a reliable and valid scale for measuring a transdiagnostic construct such as fatigue in Spanish general and clinical populations.(AU)

Population Pharmacokinetic Models of Venetoclax in Hematologic Malignancies: A Systematic Review.

Several population pharmacokinetic (PPK) models of B cell lymphoma-2 (BCL-2) venetoclax (VEN) have been developed and published to characterize the influencing factors of pharmacokinetics in hematologic malignancies. This review described PPK models of VEN examining the magnitude and types of covariate effects in PK parameters, as well as identified areas that require further investigation in order to facilitate their use. Currently, there are six analyses on PPK models of VEN summarized in this review. Most analyses described the pharmacokinetics of VEN with a two-compartment model and all covariates are categorical. The median estimated apparent clearance (CL/F) was 446 L/Day and apparent volume of distribution of the central compartment (V2/F) was 114.5 L. The median IIV of CL/F reported was 39.5% and V2/F was 46.7%. Most commonly, CYP3A inhibitors, OATP1B3 inhibitors and rituximab co-administration were found to be significant covariates on CL/F. In addition, sex and population were influential covariates on V2/F. A detailed description of the characteristics of PPK models of VEN is provided in this review, as well as the effects of covariates on the PK parameters. For future development of the VEN PPK model, CYP3A inhibitors, rituximab co-administration, OATP1B1 transporter inhibitors, sex, population, and food might be considered. Further research and comprehensive investigations should be undertaken to explore reference ranges for therapeutic drug monitoring, define the potential role of patients with cerebrospinal fluid complications, and assess new or potential covariates. These endeavors will facilitate the development of personalized VEN therapy.

Synergizing pharmacometrics and pharmacovigilance for medication error management: the case of secukinumab.

PURPOSE: To demonstrate the effective integration of pharmacometrics and pharmacovigilance in managing medication errors, highlighted by a case involving secukinumab in a patient with hidradenitis suppurativa. METHODS: We present the case of a 41-year-old male with progressive hidradenitis suppurativa, unresponsive to multiple antibiotic regimens and infliximab treatment. Due to a medication error, the patient received 300 mg of secukinumab daily for 4 days instead of weekly, totaling 1200 mg. The regional pharmacovigilance center assessed potential toxicity, and a pharmacometric analysis using a population pharmacokinetic model was performed to inform dosing adjustments. RESULTS: Clinical data indicated that the received doses were within a non-toxic range. No adverse effects were observed. Pharmacometric simulations revealed a risk of underexposure due to the dosing error. Based on these simulations, it was recommended to restart monthly secukinumab injections on day 35 after the initial dose. Measured plasma concentrations before re-administration confirmed the model's accuracy. CONCLUSION: This case highlights the crucial collaboration between clinical services, pharmacovigilance, and pharmacometrics in managing medication errors. Such interdisciplinary efforts ensure therapeutic efficacy and patient safety by maintaining appropriate drug exposure levels.

Construction of 13-locus X-STR multiplex PCR system that reinforces Argus X-12 kit discrimination capacity: Application to the Malay population.

Closely linked groups of markers on the X chromosome are very useful for testing complex kinship relationships involving X-STR transmission. The Argus X-12 kit, a unique commercially available kit, can obtain haplotypes of 4 linkage groups (LGs) consisting of 3 markers. Although many population data have been reported for forensic purposes, differences in discrimination ability exist between LG1 and LG2, 3, and 4 in East Asian populations, and the data of this kit would become more useful if the discrimination ability of the latter groups were increased. Therefore, for matches found using this kit for some linkage group data, then to increase the identification ability, we additionally introduced 13 X-STR loci and established a method allowing comparison using data from 25 loci. The 13X-STRs add two locus data to each of LG2, 3, and 4, and also add two closely linked group (CLG) data between LG2 and 3 and LG3 and 4 in one multiplex PCR. Assessment of this method for a Malay population for which data by Argus X-12 had already been reported showed that the frequencies of distinct haplotypes in LG2, 3, and 4 were increased by 33.0-42.6 %, and frequencies of unique haplotypes increased by 45.4-59.2 %. The respective haplotype diversity values of the additional 3-locus and 4-locus CLGs were 0.9838 and 0.9939, which helps to improve discriminatory power and to predict recombination locations on the X chromosome. Although we have been testing these loci with Japanese subjects, this system would also be useful for the Malay population.

Population interaction network in representative gravitational search algorithms: Logistic distribution leads to worse performance.

In this paper, a novel study on the way inter-individual information interacts in meta-heuristic algorithms (MHAs) is carried out using a scheme known as population interaction networks (PIN). Specifically, three representative MHAs, including the differential evolutionary algorithm (DE), the particle swarm optimization algorithm (PSO), the gravitational search algorithm (GSA), and four classical variations of the gravitational search algorithm, are analyzed in terms of inter-individual information interactions and the differences in the performance of each of the algorithms on IEEE Congress on Evolutionary Computation 2017 benchmark functions. The cumulative distribution function (CDF) of the node degree obtained by the algorithm on the benchmark function is fitted to the seven distribution models by using PIN. The results show that among the seven compared algorithms, the more powerful DE is more skewed towards the Poisson distribution, and the weaker PSO, GSA, and GSA variants are more skewed towards the Logistic distribution. The more deviation from Logistic distribution GSA variants conform, the stronger their performance. From the point of view of the CDF, deviating from the Logistic distribution facilitates the improvement of the GSA. Our findings suggest that the population interaction network is a powerful tool for characterizing and comparing the performance of different MHAs in a more comprehensive and meaningful way.

The Rapid Assessment of Avoidable Blindness survey: Review of the methodology and protocol for the seventh version (RAAB7).

The Rapid Assessment of Avoidable Blindness (RAAB) is a population-based cross-sectional survey methodology used to collect data on the prevalence of vision impairment and its causes and eye care service indicators among the population 50 years and older. RAAB has been used for over 20 years with modifications to the protocol over time reflected in changing version numbers; this paper describes the latest version of the methodology-RAAB7. RAAB7 is a collaborative project between the International Centre for Eye Health and Peek Vision with guidance from a steering group of global eye health stakeholders. We have fully digitised RAAB, allowing for fast, accurate and secure data collection. A bespoke Android mobile application automatically synchronises data to a secure Amazon Web Services virtual private cloud when devices are online so users can monitor data collection in real-time. Vision is screened using Peek Vision's digital visual acuity test for mobile devices and uncorrected, corrected and pinhole visual acuity are collected. An optional module on Disability is available. We have rebuilt the RAAB data repository as the end point of RAAB7's digital data workflow, including a front-end website to access the past 20 years of RAAB surveys worldwide. This website ( https://www.raab.world) hosts open access RAAB data to support the advocacy and research efforts of the global eye health community. Active research sub-projects are finalising three new components in 2024-2025: 1) Near vision screening to address data gaps on near vision impairment and effective refractive error coverage; 2) an optional Health Economics module to assess the affordability of eye care services and productivity losses associated with vision impairment; 3) an optional Health Systems data collection module to support RAAB's primary aim to inform eye health service planning by supporting users to integrate eye care facility data with population data.

In 2020 there were an estimated 1.1 billion people with vision impairment globally. Vision impairment negatively affects people's quality of life, social inclusion and productivity. The Rapid Assessment of Avoidable Blindness (RAAB) survey tool collects information about the vision and eye health of people aged 50 years and older in a defined population. It has been used worldwide for over 20 years to inform eye health service planning. This paper outlines the current survey methodology and summarises recent and upcoming developments. The RAAB project team has updated the survey to allow users to measure vision and collect other information on mobile devices (telephones or tablets) and send the findings directly to a central computer for automated analysis. The project team has built a new website to store this information and to allow anyone interested to find out more about the surveys done to date. The RAAB project continues to develop new features to make the information collected in surveys more useful for eye health service planning and eye health advocacy.

Molecular analysis of genetic mutations in non-small cell lung cancer in Morocco.

Non-small cell lung cancer (NSCLC) is a significant global health issue with diverse molecular profiles affecting treatment responses. Yet, NSCLC's molecular epidemiology in Morocco is largely unexplored. This study focuses on NSCLC genetic mutations, specifically in adenocarcinoma, among Moroccan patients to contribute to understanding NSCLC in this population. Ninety-four patients diagnosed with lung adenocarcinoma were analyzed. Formalin-fixed paraffin-embedded tissue samples were processed, and deoxyribonucleic acid (DNA)/ribonucleic acid (RNA) was extracted using standardized protocols. Mutations were detected using the AmoyDx Pan Lung Cancer Polymerase Chain Reaction (PCR) Panel kit, and their frequencies were assessed through statistical analysis. Epidermal Growth Factor Receptor (EGFR) mutations were detected in 22.34% of patients, predominantly exon 19 deletions (66.66%) and exon 21 L858R mutations (23.80%). Anaplastic lymphoma kinase (ALK) gene fusion was observed in 3.19% of patients, and KRAS mutations in 1.06%. No mutations were found in other tested genes. A slightly higher mutation rate was noted in females (54.16%) compared to males (45.84%). The study reveals a distinct mutation profile in Moroccan NSCLC patients, with a notable prevalence of EGFR mutations, albeit lower than in some Asian populations. The significance of EGFR mutations in treatment response aligns with global findings, highlighting the importance of understanding regional molecular variations for personalized therapy. Despite limitations in sample size and clinical data, this study sheds light on the genetic landscape of NSCLC in Morocco. The observed mutation rates, particularly in EGFR, underscore the potential for targeted therapies in Moroccan NSCLC patients, emphasizing the need for further research to refine treatment strategies tailored to this population.

A targeted educational intervention increases oral anticoagulation rates in high-risk atrial fibrillation patients.

Background: Anticoagulation is the cornerstone of atrial fibrillation (AF) management for stroke prevention. Recently, we showed that oral anticoagulation (OAC) rates of AF patients in a large U.S. multispecialty health system are >80%. Objective: The purpose of this study was to improve OAC rates in AF patients via an educational intervention targeted to primary care providers with low OAC rates. Methods: Primary care clinicians were stratified by proportions of their AF patients at elevated stroke risk not taking anticoagulation medication. Clinicians with the lowest rates of anticoagulation were assigned to a target group receiving an educational program consisting of E-mail messaging summarizing anticoagulation guidelines. All other clinicians were assigned to a comparison group (CG). Data from a 6-month lead-in phase were compared with a 6-month follow-up period to determine whether the proportion of AF patients treated with OACs had changed. Results: Of the 141 primary care clinicians with patients who met the inclusion criteria, 36 (25.53%) were assigned to the educational group (EG) and 105 (74.47%) to the CG. At baseline, there was a significant difference in percent of high-risk AF patients who were untreated in the EG (20.65%) compared to the high-risk patients who were untreated in the CG (13.64%; P = .001). After the educational intervention, high-risk AF patients without anticoagulation decreased in both EG (15.47%; P = .047) and CG (10.14%; P = .07), with greater absolute reduction in the EG (5.19% vs 3.50%). Conclusion: A targeted education program was associated with increased anticoagulation rates for AF patients at high risk for stroke.

Factors Associated With Extrapulmonary Tuberculosis in Southeastern Mexico: A Case-Control Study.

INTRODUCTION: Extrapulmonary tuberculosis (EPTB) is a disease that can affect any organ or tissue. Due to its potential to cause more dangerous sequelae and the barriers to its timely diagnosis, greater clinical awareness of this disease is crucial. This study aimed to identify the factors associated with EPTB in the population of Oaxaca, Mexico. METHODS: This is an unpaired case-control study. The cases were patients with EPTB+ while the controls were patients with pulmonary tuberculosis (PTB+) registered in the Tuberculosis Epidemiological Surveillance System. Sociodemographic, clinical, and microbiological variables were recovered. Bivariate analyses were performed and logistic regression analyses were performed to calculate the odds ratio (OR). RESULTS: A total of 75 EPTB+ cases and 300 PTB+ controls were included. Of the total sample, 57.1% were men and 60.3% indigenous. The most frequent clinical presentations of EPTB+ were nodal (21.3%), miliary (21.3%), and breast (20.0%). According to logistic regression analysis, age <40 years (OR: 2.25 (95% CI: 1.13-4.49), female sex (OR: 1.92 (95% CI: 1.03-3.56)], urban residence (OR: 2.25 (95% CI: 1.11-4.55)), comorbidity with human immunodeficiency virus/acquired immunodeficiency syndrome (HIV/AIDS) (OR: 3.46 (95% CI: 1.31-9.10)), dyspnea (OR: 2.67 (1.22-5.82)), and adenopathy (OR: 3.38 (95% CI: 1.42-8.06)) were positively associated with EPTB+. CONCLUSION: These results can serve as a basis for screening EPTB+, thus improving the preventive and diagnostic capacity of local health services, taking as a starting point women under 40 years of age and patients with HIV/AIDS in urban areas, as well as the presence of adenopathy and dyspnea as clinical characteristics of the disease.

Prognostic value of body mass index for first-line chemoimmunotherapy combinations in advanced non-small cell lung cancer in Chinese population.

Background: Few studies have examined the correlation between body mass index (BMI) and effectiveness of first-line chemoimmunotherapy in patients with advanced non-small cell lung cancer (NSCLC); moreover, the conclusion remains elusive and no such studies have been conducted in the Chinese population. Our study aimed to validate the predictive significance of BMI in Chinese patients with advanced NSCLC receiving first-line chemoimmunotherapy combinations. Methods: Data of patients with advanced NSCLC treated with first-line chemoimmunotherapy between June 2018 and February 2022 at three centers were retrieved retrospectively. The association between baseline BMI with progression-free survival (PFS) and overall survival (OS) was evaluated using the Kaplan-Meier method and Cox regression models. BMI was categorized according to the World Health Organization criteria. Results: Of the included 805 patients, 5.3 % were underweight, 63.4 % had normal weight, 27.8 % were overweight, and 3.5 % were obese. Survival analysis showed that patients in the high BMI group had significantly better PFS (p = 0.012) and OS (p = 0.014) than those in the low BMI group. Further, patients in the overweight subgroup had better PFS (p = 0.036) and OS (p = 0.043) compared to the normal weight population. The results of Cox regression analysis confirmed the correlations between BMI and prognosis of advanced NSCLC patients receiving first-line chemoimmunotherapy combinations. Conclusions: Baseline BMI affected the clinical outcomes of first-line chemoimmunotherapy combinations in patients with advanced NSCLC, and was especially favorable for the overweight subgroup.

Research on the health status and influencing factors of the older adult floating population in Shanghai.

Introduction: Over the past decade, against the dual background of population aging and mobility, the older adult/adults floating population has become a new type of mobile group in China, continually congregating in large cities, posing significant challenges to the socio-economic development, eldercare services, and public management of these metropolises. Shanghai, as a mega-city and the economic center of the China, is typically representative of the national population. Methods: Based on the dynamic monitoring data of Shanghai's floating population in 2018, this research uses mathematical statistics and binary Logistic regression models. Objective: This research analyzes the demographic characteristics and health status of the older adult/adults floating population in Shanghai in the new era and reveals its primary influencing factors. Results and discussion: (1) A prominent contradiction in the scale and structure of the older adult/adults floating population, with widowed and low-educated mobile older adult/adults requiring attention. (2) There is a lack of health knowledge, and the proportion of local reimbursement is low. Over 90% of migrant older adult/adults self-assessed their health (with a very few unable to care for themselves), far higher than the proportion of older adult/adults who are not sick (injured) or uncomfortable (actually healthy), which exceeds 70%. The health status of migrant older adult/adults deteriorates with age, and those who have never attended school and live alone have the worst health status. (3) Older adult/adults people with advanced age and low educational levels are at risk of health issues, while a better living environment can reduce the risk of illness in the older adult/adults floating population. Low family income, poor housing affordability, and the medical burden brought about by illness can easily lead to older adult/adults floating populations falling into the trap of older adult/adults poverty, and older adult/adults people from central regions and those who migrate along have difficulty adapting to city life, leading to poor self-assessed health. Meanwhile, community/enterprise health education helps to enhance the health protection awareness of the older adult/adults floating population. Finally, based on the governance concept of "mobility publicness," several public management and service optimization strategies for social support for the older adult/adults floating population in Shanghai are proposed.

Changes in alcohol consumption and binge drinking during the COVID-19 pandemic among American Indians residing in California and Oklahoma.

Background: This study explored the increased quantity and frequency of alcohol use in the American Indian (AI) population during the COVID-19 pandemic.Objectives: The aims of this study were to explore possible associations between covariables and both binge drinking and alcohol consumption during COVID-19.Methods: This cross-sectional survey study analyzed data from a sample of AI individuals (63% female) residing in California (n = 411) and Oklahoma (n = 657) between October 2020-January 2021. Analysis included summary statistics and multivariable logistic regression, including a variety of socio-economic, COVID-19 concern, and tobacco and marijuana use variables.Results: One or more alcohol binge episodes were reported between October 2020-January 2021 in 19.3% of participants and elevated overall alcohol consumption was reported by 21.6% of participants. Higher odds of elevated alcohol consumption occurred in women and those following more social distancing measures. The odds of binge drinking or elevated alcohol consumption in those using both marijuana and tobacco (aOR/ adjusted odds ratio:18.9, 95% CI = 8.5, 42.2, and aOR:3.9, 95% CI = 1.7, 8.6, respectively) were higher compared to those using neither. Similarly, the odds of binge drinking or elevated alcohol consumption in those using tobacco only (aOR:4.7, 95% CI = 2.9, 7.7 and aOR: 2.0, 95% CI = 1.1, 3.5, respectively) were higher compared to those using neither.Conclusions: This study found high rates of alcohol use and bingeing during the COVID-19 pandemic. Offering collaborative, culturally sensitive, and affordable support services are important components of intervention and preparation for future stressful events on local, as well as global levels.

Egypt genome: Towards an African new genomic era.

BACKGROUND: Studying the human genome is crucial to embrace precision medicine through tailoring treatment and prevention strategies to the unique genetic makeup and molecular information of individuals. After human genome project (1990-2003) generated the first full sequence of a human genome, there have been concerns towards Northern bias due to underrepresentation of other populations. Multiple countries have now established national genome projects aiming at the genomic knowledge that can be harnessed from their populations, which in turn can serve as a basis for their health care policies in the near future. AIM OF REVIEW: The intention is to introduce the recently established Egypt Genome (EG) to delineate the genomics and genetics of both the modern and Ancient Egyptian populations. Leveraging genomic medicine to improve precision medicine strategies while building a solid foundation for large-scale genomic research capacity is the fundamental focus of EG. KEY SCIENTIFIC CONCEPTS: EG generated genomic knowledge is predicted to enrich the existing human genome and to expand its diversity by studying the underrepresented African/Middle Eastern populations. The insightful impact of EG goes beyond Egypt and Africa as it fills the knowledge gaps in health and disease genomics towards improved and sustainable genomic-driven healthcare systems for better outcomes. Promoting the integration of genomics into clinical practice and spearheading the implementation of genomic-driven healthcare and precision medicine is therefore a key focus of EG. Mining into the wealth of Ancient Egyptian Genomics to delineate the genetic bridge between the contemporary and Ancient Egyptian populations is another excitingly unique area of EG to realize the global vision of human genome.

Climate change fluctuations can increase population abundance and range size.

Climate change threatens many species by a poleward/upward movement of their thermal niche. While we know that faster movement has stronger impacts, little is known on how fluctuations of niche movement affect population outcomes. Environmental fluctuations often affect populations negatively, but theory and experiments have revealed some positive effects. We study how fluctuations around the average speed of the niche impact a species' persistence, abundance and realized niche width under climate change. We find that the outcome depends on how fluctuations manifest and what the relative time scale of population growth and climate fluctuations are. When populations are close to extinction with the average speed, fluctuations around this average accelerate population decline. However, populations not yet close to extinction can increase in abundance and/or realized niche width from such fluctuations. Long-lived species increase more when their niche size remains constant, short-lived species increase more when their niche size varies.

Generation of realistic virtual adult populations using a model-based copula approach.

Incorporating realistic sets of patient-associated covariates, i.e., virtual populations, in pharmacometric simulation workflows is essential to obtain realistic model predictions. Current covariate simulation strategies often omit or simplify dependency structures between covariates. Copula models are multivariate distribution functions suitable to capture dependency structures between covariates with improved performance compared to standard approaches. We aimed to develop and evaluate a copula model for generation of adult virtual populations for 12 patient-associated covariates commonly used in pharmacometric simulations, using the publicly available NHANES database, including sex, race-ethnicity, body weight, albumin, and several biochemical variables related to organ function. A multivariate (vine) copula was constructed from bivariate relationships in a stepwise fashion. Covariate distributions were well captured for the overall and subgroup populations. Based on the developed copula model, a web application was developed. The developed copula model and associated web application can be used to generate realistic adult virtual populations, ultimately to support model-based clinical trial design or dose optimization strategies.

Age Estimation by Machine Learning and CT-Multiplanar Reformation of Cranial Sutures in Northern Chinese Han Adults.

OBJECTIVES: To establish age estimation models of northern Chinese Han adults using cranial suture images obtained by CT and multiplanar reformation (MPR), and to explore the applicability of cranial suture closure rule in age estimation of northern Chinese Han population. METHODS: The head CT samples of 132 northern Chinese Han adults aged 29-80 years were retrospectively collected. Volume reconstruction (VR) and MPR were performed on the skull, and 160 cranial suture tomography images were generated for each sample. Then the MPR images of cranial sutures were scored according to the closure grading criteria, and the mean closure grades of sagittal suture, coronal sutures (both left and right) and lambdoid sutures (both left and right) were calculated respectively. Finally taking the above grades as independent variables, the linear regression model and four machine learning models for age estimation (gradient boosting regression, support vector regression, decision tree regression and Bayesian ridge regression) were established for northern Chinese Han adults age estimation. The accuracy of each model was evaluated. RESULTS: Each cranial suture closure grade was positively correlated with age and the correlation of sagittal suture was the highest. All four machine learning models had higher age estimation accuracy than linear regression model. The support vector regression model had the highest accuracy among the machine learning models with a mean absolute error of 9.542 years. CONCLUSIONS: The combination of skull CT-MPR and machine learning model can be used for age estimation in northern Chinese Han adults, but it is still necessary to combine with other adult age estimation indicators in forensic practice.

Adults Ischium Age Estimation Based on Deep Learning and 3D CT Reconstruction.

OBJECTIVES: To develop a deep learning model for automated age estimation based on 3D CT reconstructed images of Han population in western China, and evaluate its feasibility and reliability. METHODS: The retrospective pelvic CT imaging data of 1 200 samples (600 males and 600 females) aged 20.0 to 80.0 years in western China were collected and reconstructed into 3D virtual bone models. The images of the ischial tuberosity feature region were extracted to create sex-specific and left/right site-specific sample libraries. Using the ResNet34 model, 500 samples of different sexes were randomly selected as training and verification set, the remaining samples were used as testing set. Initialization and transfer learning were used to train images that distinguish sex and left/right site. Mean absolute error (MAE) and root mean square error (RMSE) were used as primary indicators to evaluate the model. RESULTS: Prediction results varied between sexes, with bilateral models outperformed left/right unilateral ones, and transfer learning models showed superior performance over initial models. In the prediction results of bilateral transfer learning models, the male MAE was 7.74 years and RMSE was 9.73 years, the female MAE was 6.27 years and RMSE was 7.82 years, and the mixed sexes MAE was 6.64 years and RMSE was 8.43 years. CONCLUSIONS: The skeletal age estimation model, utilizing ischial tuberosity images of Han population in western China and employing the ResNet34 combined with transfer learning, can effectively estimate adult ischium age.