A new X-ray based osteoporosis screening tool provides accurate and precise assessment of phalanx bone mineral content

Osteoporosis screening using machine learning and electromagnetic waves

Osteoporosis is a disease characterized by impairment of bone microarchitecture that causes high socioeconomic impacts in the world because of fractures and hospitalizations. Although dual-energy X-ray absorptiometry (DXA) is the gold standard for diagnosing the disease, access to DXA in developing countries is still limited due to its high cost, being present only in specialized hospitals. In this paper, we analyze the performance of Osseus, a low-cost portable device based on electromagnetic waves that measures the attenuation of the signal that crosses the medial phalanx of a patient's middle finger and was developed for osteoporosis screening. The analysis is carried out by predicting changes in bone mineral density using Osseus measurements and additional common risk factors used as input features to a set of supervised classification models, while the results from DXA are taken as target (real) values during the training of the machine learning algorithms. The dataset consisted of 505 patients who underwent osteoporosis screening with both devices (DXA and Osseus), of whom 21.8% were healthy and 78.2% had low bone mineral density or osteoporosis. A cross-validation with k-fold = 5 was considered in model training, while 20% of the whole dataset was used for testing. The obtained performance of the best model (Random Forest) presented a sensitivity of 0.853, a specificity of 0.879, and an F1 of 0.859. Since the Random Forest (RF) algorithm allows some interpretability of its results (through the impurity check), we were able to identify the most important variables in the classification of osteoporosis. The results showed that the most important variables were age, body mass index, and the signal attenuation provided by Osseus. The RF model, when used together with Osseus measurements, is effective in screening patients and facilitates the early diagnosis of osteoporosis. The main advantages of such early screening are the reduction of costs associated with exams, surgeries, treatments, and hospitalizations, as well as improved quality of life for patients.

Prescreening for osteoporosis with forearm bone densitometry in health examination population

BACKGROUND

Early detection and timely prophylaxis can retard the progression of osteoporosis. The purpose of this study was to determine the validity of peripheral Dual Energy X-ray Absorptiometry (DXA) test for osteoporosis screening. We examined peripheral bone mineral density (BMD) using AKDX-09 W-I DXA densitometer. Firstly, we acquired BMD data from manufacturer-supplied density-gradient phantoms and 30 volunteers to investigate its accuracy and precision, then we measured BMD for 150 volunteers using both AKDX (left forearm) and Hologic Discovery Wi (left forearm, left hip and L1 - L4 vertebrae) simultaneously. Correlation relationship of BMD results acquired from two instruments was assessed by simple linear regression analysis, the Receiver Operating Characteristic (ROC) curves and Areas Under the Curves (AUCs) were evaluated for the diagnostic value of left forearm BMD measured by AKDX in detecting osteoporosis.

RESULTS

In vitro precision errors of AKDX BMD were 0.40, 0.20, 0.19%, respectively, on low-, medium-, and high-density phantom; in vivo precision was 1.65%. Positive correlation was observed between BMD measured by AKDX and Hologic at the forearm (r = 0.670), L1-L4 (r = 0.430, femoral neck (r = 0.449), and total hip (r = 0.559). With Hologic measured T-score as the gold standard, the sensitivity of AKDX T-score < - 1 for identifying suboptimal bone health was 63.0 and 76.1%, respectively, at the distal one-third radius and at any site, and the specificity was 73.9 and 90.0%, respectively; the AUCs were 0.708 and 0.879. The sensitivity of AKDX T-score ≤ - 2.5 for identifying osteoporosis at the distal one-third radius and at any site was 76.9 and70.4%, respectively, and the specificity was 80.4 and 78.0%, respectively; the AUCs were 0.823 and 0.778.

CONCLUSIONS

Peripheral DXA appears to be a reliable tool for prescreening for osteoporosis.

Does Bone Mineral Density Differ between Fan-Beam and Pencil-Beam?: A Meta-Analysis and Systemic Review

Background

Dual energy X-ray absorptiometry (DXA) has evolved from pencil-beam (PB) to narrow fan-beam (FB) densitometers. We performed a meta-analysis of the available observational studies to determine how different modes of DXA affect bone mineral density (BMD) measurements.

Methods

A total of 1,233 patients (808 women) from 14 cohort studies were included. We evaluated the differences in BMD according to the DXA mode: PB and FB. Additionally, we evaluated the differences in BMD between the 2 types of FB mode: FB (Prodigy) and the most recent FB (iDXA). Pairwise meta-analysis was performed, and weighted mean differences (WMD) were calculated for (total lumbar, total hip, and total body).

Results

No significant difference was observed in total lumbar (pooled WMD, −0.013; P=0.152) and total hip BMD (pooled WMD, −0.01; P=0.889), between PB and FB. However, total body BMD was significantly lower in the PB compared to the FB group (pooled WMD, −0.014; P=0.024). No significant difference was observed in lumbar BMD (pooled WMD, −0.006; P=0.567), total hip (pooled WMD, −0.002; P=0.821), and total body (pooled WMD, 0.015; P=0.109), between Prodigy and iDXA.

Conclusions

The results of this study warrant the recommendation that correction equations should not be used when comparing BMD from different modes. Further research is still needed to highlight the ways in which differences between DXA systems can be minimized.

Feasibility of osteoporosis screening by dual-energy radiographic absorptiometry of the phalanx

A new dual-energy radiographic absorptiometry-based technique is presented as a cost-effective method for mass osteoporosis screening. Designed for use in a dental health care setting, we propose a method and device for bone mineral density (BMD) assessment using the middle phalanx of the 3rd digit as our anatomical measurement site. Our 2-staged project includes the development of the prototype to carry out the measurement and the execution of a small pilot study to determine the efficacy of the method and device. Fifty subjects from the general adult population (age range: 25-82 yr), wherein 10 normal subjects (5 females and 5 males) and 40 target group subjects (30 females and 10 males) who were at risk for osteoporosis (as assessed qualitatively through questionnaire responses) were evaluated with our method. The BMD values obtained from the normal and target groups were significantly different (p<0.0001). Phantom measurements to determine the bias and coefficient of variation of the technique yielded values of 1.9% and 7%, respectively. The proposed technique could provide a relatively inexpensive and widely available means for mass osteoporosis screening. Further validation of this method, to include comparison to a gold standard, such as dual-energy X-ray absorptiometry, is warranted.

Hand osteoarthritis and bone mineral density in postmenopausal women; clinical relevance to hand function, pain and disability

OBJECTIVE

The aim of the present study was to assess phalangeal bone mineral density (BMD) in postmenopausal females with hand osteoarthritis (OA) and to correlate the measured levels with the radiographic OA grade, pain, function and disability of the hand.

METHODS

The study group constituted 40 postmenopausal women with hand OA (range; 45-83 years). Socio-demographic data were collected. They underwent a comprehensive clinical examination of joint status and health outcome measure including Australian Canadian (AUSCAN) OA hand index. Hand radiographs were quantified and graded according to Kellgren and Lawrence (K-L) scoring system. Bone mineral content (BMC) and BMD of the third finger were measured using the accuDEXA (Schick, New York, NY). Twenty females matched for age and years of menopause were studied as a control group.

RESULTS

Phalangeal BMC and BMD were significantly reduced in women with hand OA compared to controls and related to radiological erosive OA. The AUSCAN pain and function subscales were worse in proportion to the severity of hand OA. OA X-ray score was significantly associated with reduced right grip strength, pain, and function scales while, decreased BMD was related to Ritchie index and pain scale.

CONCLUSION

Postmenopausal women with clinical and radiological hand erosive OA are at risk of development of hand osteoporosis (OP). Phalangeal bone densitometry is an objective reproducible investigation. Poor physical function due to increased pain associated with increasing severity of radiographic hand OA leads to worse BMD results.

Development of a compact MRI system for measuring the trabecular bone microstructure of the finger

A compact MRI system for measuring the trabecular bone (TB) microstructure of the finger using a high-field-strength (1.0T) permanent magnet was developed. The entire system was installed in a 0.6 mx1.2 m space. One male and 36 female subjects participated in the imaging experiments. The TB of the distal phalanx of the middle finger was imaged at a voxel resolution of (160 microm)3 using a three-dimensional (3D) driven equilibrium spin-echo (SE) imaging sequence (imaging time=approximately 14 min). The image data sets obtained yielded two distinct peaks for the bone and marrow in image intensity histograms when no motion was present. The structural parameters obtained through 3D image analysis show that this compact system is potentially useful for evaluating bone quality.

A comparison of dual energy X-ray absorptiometry of the hip and accuDEXA of the finger for the diagnosis of osteoporosis in men on androgen deprivation therapy for advanced prostate cancer

Dual energy X-ray absorptiometry (DEXA) of the hip or spine has been shown to be an effective screening tool for osteoporosis in men undergoing androgen deprivation therapy (ADT) for advanced carcinoma of the prostate. A less expensive alternative to DEXA is the use of peripheral scanners, such as accuDEXA, which measures bone mineral density (BMD) the finger. In this paper, we reviewed 59 patients on ADT who underwent both accuDEXA scan of the non-dominant hand and DEXA scan of the hip. The mean T-scores calculated by the two techniques were similar; however, the individual T-scores correlated poorly with each other. We conclude that men who require ADT for prostate cancer should undergo standard DEXA of the hip for osteoporosis screening.

Ability of peripheral DXA measurement to diagnose osteoporosis as assessed by central DXA measurement

In order to evaluate the utility of peripheral measurement of bone mineral density (BMD) in the diagnosis of osteoporosis, we measured BMD at the spine and femoral neck with central dual-energy X-ray absorptiometry (DXA), at phalanx with AccuDXA (Schick) as well as proximal and distal forearm with pDXA (Norland) in 835 women ranging in age from 20 to 85 yr. In receiver operating characteristic (ROC) curves, where a positive case was defined as a T-score < or = -2.5 either on spine or femoral neck, the areas under the curve were not significantly different between sites. At a T-score of -2.5 as determined by each peripheral apparatus, sensitivity and specificity were, respectively, 0.39 and 0.95 for phalanx and 0.75 and 0.85 for proximal forearm whereas they were 0.42 and 0.96 for distal forearm. Using optimal absolute BMD cutoff values improved the results. Sensitivity and specificity were, respectively, 0.79 and 0.83 for phalanx at an absolute BMD value of 0.436 and 0.84 and 0.79 for proximal forearm at a value of 0.703, whereas they were 0.90 and 0.75 for distal forearm at a value of 0.208. Combining the two forearm measurements improves the results slightly. At cutoff values of 0.641 and 0.252, respectively for proximal and distal forearms, sensitivity was 0.83 and specificity was 0.84. Therefore, a peripheral measurement of BMD together with a good clinical evaluation of the osteoporosis risk profile of the patient, can be an interesting tool for the diagnosis of osteoporosis in areas where central DXA is not available.

Relationship between phalangeal bone density and risk of vertebral fracture

The aims of our study were to determine the relationship between bone mineral density (BMD) measurements of the phalanges obtained with the accuDEXA and recent vertebral fractures. To determine whether osteoarthritis of the hands affects phalangeal BMD measurements, and to illustrate the conversion of phalangeal BMD measurements to absolute fracture risk estimates for clinical application. The prospective Hawaii Osteoporosis Study began in 1981, and incident vertebral fractures were identified from serial radiographs obtained at approx 2-yr intervals. Vertebral fractures occurring between 1993 and 1994 and 1997 and 1998 were compared to phalangeal BMD measurements obtained in 1997-1998. A total of 199 women participated in this case-control study. The association of the phalangeal BMD measurements with vertebral fractures was examined in age-adjusted, logistic regression models. Results are expressed as odds ratios (ORs) per SD difference in the phalangeal BMD measurements. Osteoarthritis of the hands was graded according to the Kellgren-Lawrence scale. There were 34 incident fractures since the eighth examination in 1993-1994. For vertebral fractures, the OR per SD of phalangeal BMD was 1.5 (1.0-2.1). Phalangeal BMD was not influenced significantly by established osteoarthritis (p = 0.68). Phalangeal BMD measurements obtained with the accuDEXA device relate to recent vertebral fractures and can be used to identify women at high risk of fractures. The phalangeal BMD measurements obtained with this device are not significantly influenced by the presence of osteoarthritis of the hands.

What is the role of serial bone mineral density measurements in patient management?

The ability of dual X-ray absorptiometry (DXA) to monitor bone mineral density (BMD) has been well documented in epidemiologic and pharmaceutical trials. However, its application to monitoring of patients in clinical practice has been subject to recent controversies. Despite these controversies, most clinical centers rely on DXA for monitoring of patients, and therefore guidance is needed. In this article, we report the positions developed by an expert panel of the International Society for Clinical Densitometry on the use of densitometry for the serial measurement of bone mass for monitoring change in BMD. The panel found DXA to be a precise method of measuring change in BMD if used with an appropriate level of least significant change (LSC), at anatomic sites with good precision and response to therapy, and at 1- to 2-yr time intervals. Monitoring is acceptable for determining when therapy is indicated, and if an agent is not therapeutically effective (i.e., when bone loss occurs despite treatment). Each densitometry center should perform an in vivo precision study on individuals similar to the patient population at the center and determine LSC at a 95% confidence level. If such a precision study cannot be performed, benchmark precision might be used, although there was no agreement on what values should be used. The PA spine is the preferred anatomic site for monitoring. The total hip can be used when the spine study is technically invalid. We conclude with recommendations for further research.

Bone mineral measurement of phalanges: comparison of radiographic absorptiometry and area dual X-ray absorptiometry

With a standard, image-intensifier-based, digital radiographic system, high-spatial-resolution images of the hand were acquired for analysis of phalangeal bone mineral density with dual x-ray absorptiometry (DXA). Results with phalangeal DXA had precision of plus or minus 0.67% and accuracy of 4.1% and correlated well with those with radiographic absorptiometry. This phalangeal DXA technique is potentially useful for clinical diagnosis of osteoporosis.

Comparison of bone mineral density of the phalanges, lumbar spine, hip, and forearm for the assessment of osteoporosis in postmenopausal women

The objective of this study was to compare peripheral bone mineral density (BMD) of the phalanges with BMD of the lumbar spine, total hip, femoral neck, and forearm and to determine the clinical value of measuring a single peripheral site (phalanges) in identifying postmenopausal women with osteoporosis. BMD was measured by dual energy X-ray absorptiometry using the accuDEXA((R)) (ADXA-finger) (Schick, New York, NY) and the QDR-4500 (DXA-lumbar spine, hip, forearm) (Hologic, Waltham, MA). Correlation coefficients between ADXA and DXA of the lumbar spine, total hip, femoral neck and one third radial site ranged from 0.53 to 0.73. The sensitivity of an ADXA T-score of -2.5 in identifying patients with a DXA T-score of < or = -2.5 at the femoral neck was 35%. An ADXA T-score cut point of -1.0 improved the sensitivity of ADXA in identifying patients with a femoral neck T-score of < or = -2.5 (85%), but the specificity declined from 88 to 49%. There was substantial discordance in the diagnosis of osteoporosis when a single site was measured, regardless of technique. Within the limitations of single-site measurements, BMD measured by ADXA has adequate sensitivity to identify women with low BMD at the femoral neck, if an appropriate T-score criterion is used.