Dataset Information

Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach.

ABSTRACT: BACKGROUND:Bone age assessment (BAA) is used in numerous pediatric clinical settings as well as in legal settings when entities need an estimate of chronological age (CA) when valid documents are lacking. The latter case presents itself as critical as the law is harsher for adults and granted rights along with imputability changes drastically if the individual is a minor. Traditional BAA methods have drawbacks such as exposure of minors to radiation, they do not consider factors that might affect the bone age, and they mostly focus on a single region. Given the critical scenarios in which BAA can affect the lives of young individuals, it is important to focus on the drawbacks of the traditional methods and investigate the potential of estimating CA through BAA. OBJECTIVE:This study aims to investigate CA estimation through BAA in young individuals aged 14-21 years with machine learning methods, addressing the drawbacks of research using magnetic resonance imaging (MRI), assessment of multiple regions of interest, and other factors that may affect the bone age. METHODS:MRI examinations of the radius, distal tibia, proximal tibia, distal femur, and calcaneus were performed on 465 men and 473 women (aged 14-21 years). Measures of weight and height were taken from the subjects, and a questionnaire was given for additional information (self-assessed Tanner Scale, physical activity level, parents' origin, and type of residence during upbringing). Two pediatric radiologists independently assessed the MRI images to evaluate their stage of bone development (blinded to age, gender, and each other). All the gathered information was used in training machine learning models for CA estimation and minor versus adult classification (threshold of 18 years). Different machine learning methods were investigated. RESULTS:The minor versus adult classification produced accuracies of 0.90 and 0.84 for male and female subjects, respectively, with high recalls for the classification of minors. The CA estimation for the 8 age groups (aged 14-21 years) achieved mean absolute errors of 0.95 years and 1.24 years for male and female subjects, respectively. However, for the latter, a lower error occurred only for the ages of 14 and 15 years. CONCLUSIONS:This study investigates CA estimation through BAA using machine learning methods in 2 ways: minor versus adult classification and CA estimation in 8 age groups (aged 14-21 years), while addressing the drawbacks in the research on BAA. The first achieved good results; however, for the second case, the BAA was not precise enough for the classification.

SUBMITTER: Dallora AL

PROVIDER: S-EPMC7536601 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach.

Dallora Ana Luiza AL Kvist Ola O Berglund Johan Sanmartin JS Ruiz Sandra Diaz SD Boldt Martin M Flodmark Carl-Erik CE Anderberg Peter P

JMIR medical informatics 20200921 9

<h4>Background</h4>Bone age assessment (BAA) is used in numerous pediatric clinical settings as well as in legal settings when entities need an estimate of chronological age (CA) when valid documents are lacking. The latter case presents itself as critical as the law is harsher for adults and granted rights along with imputability changes drastically if the individual is a minor. Traditional BAA methods have drawbacks such as exposure of minors to radiation, they do not consider factors that mig ...[more]

PMID: 32955457

Similar Datasets

Project description:Accurate age estimation in wildlife conservation is an important diagnostic tool in the interpretation of biological data, necropsy examination, reproductive status and population demographics. The most frequently utilized methods to age bottlenose dolphins (Tursiops truncatus) include tooth extraction; counting dental growth layer groups and dental radiography. These methods are inaccurate in dolphins > 13 years old, due to overlapping of the growth layer groups in dolphins and worn teeth. Establishing a non-invasive method of accurately aging bottlenose dolphins across the entire age range is important to long term conservation efforts to understand health status, lifespan, reproduction and survivability. A database of 126 radiographs from 94 dolphins of known chronological age was utilized to establish the stages of skeletal ossification over time. A numerical score from -1 to 8 was assigned to 16 anatomic locations on the pectoral radiograph, to create a formula to estimate age. The most informative areas to evaluate morphologically were the metaphyseal regions of the radius and ulna, and the proximal and distal epiphysis of metacarpals II and III. Third order polynomial regression calculated separate age predictor formulas for male and female dolphins, with females reaching sexual maturity earlier than males. Completion of epiphyseal closure of the long bones correlated with average sexual maturity. Managed care dolphin ages could be properly estimated with decreasing precision from within 3 months in animals < 5 years old, to within 5 years in animals > 30 years old. This diagnostic tool could also be applied to diagnose atypical ossification patterns consistent with nutritional, developmental or growth abnormalities, and identifying subclinical health issues. In conclusion, knowledge of the lifespan and the onset of sexual maturity for each species will allow this model to be applied to other cetaceans, facilitating age estimation via pectoral radiography in future research.

Project description:BackgroundThe assessment of bone age and skeletal maturity and its comparison to chronological age is an important task in the medical environment for the diagnosis of pediatric endocrinology, orthodontics and orthopedic disorders, and legal environment in what concerns if an individual is a minor or not when there is a lack of documents. Being a time-consuming activity that can be prone to inter- and intra-rater variability, the use of methods which can automate it, like Machine Learning techniques, is of value.ObjectiveThe goal of this paper is to present the state of the art evidence, trends and gaps in the research related to bone age assessment studies that make use of Machine Learning techniques.MethodA systematic literature review was carried out, starting with the writing of the protocol, followed by searches on three databases: Pubmed, Scopus and Web of Science to identify the relevant evidence related to bone age assessment using Machine Learning techniques. One round of backward snowballing was performed to find additional studies. A quality assessment was performed on the selected studies to check for bias and low quality studies, which were removed. Data was extracted from the included studies to build summary tables. Lastly, a meta-analysis was performed on the performances of the selected studies.Results26 studies constituted the final set of included studies. Most of them proposed automatic systems for bone age assessment and investigated methods for bone age assessment based on hand and wrist radiographs. The samples used in the studies were mostly comprehensive or bordered the age of 18, and the data origin was in most of cases from United States and West Europe. Few studies explored ethnic differences.ConclusionsThere is a clear focus of the research on bone age assessment methods based on radiographs whilst other types of medical imaging without radiation exposure (e.g. magnetic resonance imaging) are not much explored in the literature. Also, socioeconomic and other aspects that could influence in bone age were not addressed in the literature. Finally, studies that make use of more than one region of interest for bone age assessment are scarce.

Project description:BackgroundCalorie restriction (CR) is promoted to increase longevity, yet this regimen could lead to bone loss and fracture and therefore affect quality of life.MethodsForty-six individuals were randomized to 4 groups for 6 months: (1) healthy diet (control group); (2) 25% CR from baseline energy requirements (CR group); (3) 25% energy deficit by a combination of CR and increased aerobic exercise (CR + EX group); and (4) low-calorie diet (890 kcal/d; goal, 15% weight loss) followed by weight maintenance (LCD group). Bone mineral density (total body and hip by dual-energy x-ray absorptiometry) and serum bone markers (bone-specific alkaline phosphatase, osteocalcin, cross-linked C-telopeptide of type I collagen, and cross-linked N-telopeptide of type I collagen) were measured at baseline and after 6 months.ResultsMean +/- SE body weight was reduced by -1.0% +/- 1.1% (control), -10.4% +/- 0.9% (CR), -10.0% +/- 0.8% (CR + EX), and -13.9% +/- 0.7% (LCD). Compared with the control group, none of the groups showed any change in bone mineral density for total body or hip. Bone resorption by serum cross-linked C-telopeptide of type I collagen was increased in all 3 intervention groups, with the largest change observed in the LCD group (CR, 23% +/- 10%; CR + EX, 22% +/- 9%; and LCD, 74% +/- 16% vs control, 4% +/- 10%). Serum levels of cross-linked N-telopeptide of type I collagen were also increased in the LCD group. With regard to bone formation, bone alkaline phosphatase levels were decreased in the CR group (-23% +/- 10%) but were unchanged in the CR + EX, LCD, and control groups.ConclusionsModerate CR, with or without exercise, that preserves calcium intake for 6 months leads to large changes in body composition without significant bone loss in young adults. Longer studies with assessments of bone architecture are needed to confirm that CR nutrient-dense diets have no deleterious effect on bone health.Trial registrationclinicaltrials.gov Identifier: NCT00099151.

Project description:Background and Objectives: Women with gynecological cancers constitute a high-risk cohort for loss of bone density. International guidance stipulates women undergoing cancer treatments associated with bone loss should have a quantitative assessment of bone density. Access to Dual-energy X-ray Absorptiometry (DXA) is limited. This study aimed to assess the accuracy of opportunistic bone density measurement on staging computed tomography (CT) scans for gynaecological malignancies, in comparison to the gold standard DXA. Materials and Methods: Women with a staging CT scan of the abdomen and pelvis for a new diagnosis of gynecological cancer were recruited. DXA was performed within 6 weeks of treatment for gynaecological cancer. Lumbar bone density was measured by CT attenuation values, in Hounsfield units (HU), of the anterior trabecular region. Correlations between CT and DXA parameters were analysed. Receiver Operating Characteristic(ROC) curves for diagnosis of low bone density and osteoporosis were analysed. Results: Final cohort included 48 of 50 women recruited. There was good diagnostic accuracy for abnormal bone density and osteoporosis, with areas under the ROC curve at L1 of 0.77 (p = 0.002) and 0.80 (p = 0.020) respectively. CT-HU of 170-190 yielded sensitivities of 87-90%, positive predictive values of 75-84% and negative predictive values of 71-75% for the diagnosis of low bone mineral density. CT-HU of 90-110 yielded specificities of 85-93% for the diagnosis of osteoporosis. Moderate correlations were found between CT-HU and both DXA T-scores and diagnostic categories. Conclusions: This is the first study to assess the opportunistic application of CT in the assessment of bone health in women with gynaecological cancer, a cohort at high-risk of osteoporosis. The correlation between bone density assessment in CT-HU and DXA, and strong AUC values for the diagnosis of low bone density (0.77) and osteoporosis (0.80) support this pragmatic solution in resolving the care-gap in cancer treatment-induced bone loss, often associated with poor access to DXA.

Dataset Information

Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach.

Publications

Chronological Age Assessment in Young Individuals Using Bone Age Assessment Staging and Nonradiological Aspects: Machine Learning Multifactorial Approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets