Dataset Information

A Predictive Model for Abnormal Bone Density in Male Underground Coal Mine Workers.

ABSTRACT: The dark and humid environment of underground coal mines had a detrimental effect on workers' skeletal health. Optimal risk prediction models can protect the skeletal health of coal miners by identifying those at risk of abnormal bone density as early as possible. A total of 3695 male underground workers who attended occupational health physical examination in a coal mine in Hebei, China, from July to August 2018 were included in this study. The predictor variables were identified through single-factor analysis and literature review. Three prediction models, Logistic Regression, CNN and XG Boost, were developed to evaluate the prediction performance. The training set results showed that the sensitivity of Logistic Regression, XG Boost and CNN models was 74.687, 82.058, 70.620, the specificity was 80.986, 89.448, 91.866, the F1 scores was 0.618, 0.919, 0.740, the Brier scores was 0.153, 0.040, 0.156, and the Calibration-in-the-large was 0.104, 0.020, 0.076, respectively, XG Boost outperformed the other two models. Similar results were obtained for the test set and validation set. A two-by-two comparison of the area under the ROC curve (AUC) of the three models showed that the XG Boost model had the best prediction performance. The XG Boost model had a high application value and outperformed the CNN and Logistic regression models in prediction.

SUBMITTER: Zheng Z

PROVIDER: S-EPMC9368504 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Predictive Model for Abnormal Bone Density in Male Underground Coal Mine Workers.

Zheng Ziwei Z Chen Yuanyu Y Yang Yongzhong Y Meng Rui R Si Zhikang Z Wang Xuelin X Wang Hui H Wu Jianhui J

International journal of environmental research and public health 20220727 15

The dark and humid environment of underground coal mines had a detrimental effect on workers' skeletal health. Optimal risk prediction models can protect the skeletal health of coal miners by identifying those at risk of abnormal bone density as early as possible. A total of 3695 male underground workers who attended occupational health physical examination in a coal mine in Hebei, China, from July to August 2018 were included in this study. The predictor variables were identified through single ...[more]

PMID: 35954527

Similar Datasets

Project description:This assessment was designed to explore and characterize the airborne particles, especially for the sub-micrometer sizes, in an underground coal mine. Airborne particles present in the breathing zone were evaluated by using both (1) direct reading real-time instruments (RTIs) to measure real-time particle number concentrations in the workplaces and (2) gravimetric samplers to collect airborne particles to obtain mass concentrations and conduct further characterizations. Airborne coal mine particles were collected via three samplers: inhalable particle sampler (37 mm cassette with polyvinyl chloride (PVC) filter), respirable dust cyclone (10 mm nylon cyclone with 37 mm Zefon cassette and PVC filter), and a Tsai diffusion sampler (TDS). The TDS, a newly designed sampler, is for collecting particles in the nanometer and respirable size range with a polycarbonate filter and grid. The morphology and compositions of collected particles on the filters were characterized using electron microscopy (EM). RTIs reading showed that the belt entry had a greatly nine-times higher total particle number concentration in average (~ 34,700 particles/cm3) than those measured at both the underground entry and office building (~ 4630 particles/cm3). The belt entry exhibited not only the highest total particle number concentration, but it also had different particle size fractions, particularly in the submicron and smaller sizes. A high level of submicron and nanoparticles was found in the belt conveyor drift area (with concentrations ranging from 0.54 to 1.55 mg/m3 among three samplers). The data support that small particles less than 300 nm are present in the underground coal mine associated with dust generated from practical mining activities. The chemical composition of the air particles has been detected in the presence of Ca, Cu, Si, Al, Fe, and Co which were all found to be harmful to miners when inhaled.Supplementary informationThe online version contains supplementary material available at 10.1007/s42461-024-01140-w.

Project description:Background: In subcontinental underground mines, coal mining is carried out manually and requires many laborers to practice traditional means of coal excavation. Each task of this occupation disturbs workers' musculoskeletal order. In order to propose and practice possible ergonomic interventions, it is necessary to know what tasks (drilling and blasting, coal cutting, dumping, transporting, timbering and supporting, loading and unloading) cause disorder in either upper limbs, lower limbs, or both. Methods: To this end, R-programming, version R 3.1.2 and SPSS, software 20, were used to calculate data obtained by studying 260 workers (working at different tasks of coal mining) from 20 mines of four districts of Punjab, Pakistan. In addition, a Standard Nordic Musculoskeletal Questionnaire (SNMQ) and Rapid Upper Limb Assessment (RULA) sheet were used to collect data and to analyze postures respectively. Results: In multi regression models, significance of the five tasks for upper and lower limb disorder is 0.00, which means that task based prevalence of upper and lower limb disorders are common in underground coal mines. The results of the multiple bar chart showed that 96 coal cutters got upper limb disorders and 82 got lower limb disorders. The task of timbering and supporting was shown to be dangerous for the lower limbs and relatively less dangerous for the upper limbs, with 25 workers reporting pain in their lower limbs, and 19 workers reporting pain in their upper limbs. Documented on the RULA sheet, all tasks got the maximum possible score (7), meaning that each of these tasks pose a threat to the posture of 100% of workers. The majority of participants (182) fell in the age group of 26 to 35 years. Of those workers, 131 reported pain in the lower limbs and slight discomfort (128) in the upper limbs. The significance value of age was 0.00 for upper limb disorder and was 0.012 for lower limb disorder. Frequency graphs show age in direct proportion to severity of pain while in inverse proportion with number of repetitions performed per min. Conclusions: All findings infer that each task of underground coal mining inflicts different levels of disorder in a workers' musculoskeletal structure of the upper and lower limbs. It highlighted the need for urgent intervention in postural aspects of each task.

Project description:Mines and caves are unusual ecosystems containing unique fungi and are greatly understudied compared to other environments. The Soudan Mine in Tower, MN, an iron ore mine that closed in 1963 after operating for 80 years, was sampled to explore fungal diversity and to investigate taxa that tolerate heavy metals for potential bioprocessing technologies or as sources of bioactive molecules for drug discovery and possible biocontrol for white-nose syndrome (WNS) of bats. The mine is 714 m deep, has 18 levels and contains large quantities of wooden timbers, in contrast to many other oligotrophic subterranean environments. Fungi were cultured from samples and the ITS region was sequenced for identification and phylogenetic analysis. Results show Ascomycota are the dominant fungi followed by Basidiomycota and Mucoromycota. Out of 164 identified taxa, 108 belong to the Ascomycota and 26 and 31 to Basidiomycota and Mucoromycota, respectively. There are also 46 taxa that do not match (<97% BLAST GenBank identity) sequenced fungal species. Examples of the most commonly isolated Ascomycota include Scytalidium sp., Mariannaea comptospora, Hypocrea pachybasidioides, Oidiodendron griseum and Pochonia bulbillosa; Basidiomycota include Postia sp., Sistotrema brinkmannii, Calocera sp., Amylocorticiellum sp.; Mucoromycota include Mortierella parvispora, M. gamsii, M. hyaline, M. basiparvispora and Mortierella sp. Unusual growth forms were also found including large quantities of black rhizomorphs of Armillaria sinapina and white mycelial cords of Postia sp. mycelium, as well as Pseudogymnoascus species growing over large areas of mine walls and ceiling. The mine environment is a relatively extreme environment for fungi, with the presence of high levels of heavy metals, complete darkness and poor nutrient availability. Several genera are similar to those isolated in other extreme environments but phylogenetic analyses show differences in species between these environments. Results indicate this subterranean environment hosts a wide diversity of fungi, many of them not found in above ground environments.

Dataset Information

A Predictive Model for Abnormal Bone Density in Male Underground Coal Mine Workers.

Publications

A Predictive Model for Abnormal Bone Density in Male Underground Coal Mine Workers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets