A Machine Learning-Based Preclinical Osteoporosis Screening Tool (POST): Model Development and Validation Study.

Background: Identifying persons with a high risk of developing osteoporosis and preventing the occurrence of the first fracture is a health care priority. Most existing osteoporosis screening tools have high sensitivity but relatively low specificity. Objective: We aimed to develop an easily accessible and high-performance preclinical risk screening tool for osteoporosis using a machine learning-based method among the Hong Kong Chinese population. Methods: Participants aged 45 years or older were enrolled from 6 clinics in the 3 major districts of Hong Kong. The potential risk factors for osteoporosis were collected through a validated, self-administered questionnaire and then filtered using a machine learning-based method. Bone mineral density was measured with dual-energy x-ray absorptiometry at the clinics; osteoporosis was defined as a t score of -2.5 or lower. We constructed machine learning models, including gradient boosting machines, support vector machines, and naive Bayes, as well as the commonly used logistic regression models, for the prediction of osteoporosis. The best-performing model was chosen as the final tool, named the Preclinical Osteoporosis Screening Tool (POST). Model performance was evaluated by the area under the receiver operating characteristic curve (AUC) and other metrics. Results: Among the 800 participants enrolled in this study, the prevalence of osteoporosis was 10.6% (n=85). The machine learning-based Boruta algorithm identified 15 significantly important predictors from the 113 potential risk factors. Seven variables were further selected based on their accessibility and convenience for daily self-assessment and health care practice, including age, gender, education level, decreased body height, BMI, number of teeth lost, and the intake of vitamin D supplements, to construct the POST. The AUC of the POST was 0.86 and the sensitivity, specificity, and accuracy were all 0.83. The positive predictive value, negative predictive value, and F1-score were 0.41, 0.98, and 0.56, respectively. Conclusions: The machine learning-based POST was conveniently accessible and exhibited accurate discriminative capabilities for the prediction of osteoporosis; it might be useful to guide population-based preclinical screening of osteoporosis and clinical decision-making.

Greater habitual resveratrol intakes were associated with lower risk of hip fracture- a 1:1 matched case-control study in Chinese elderly.

The aim of the study was to testify the association of dietary resveratrol (RSV) intakes with hip fracture risk in Chinese elderly. This was a 1:1 age- and gender- matched case-control study. Eligible cases were newly diagnosed patients of hip fracture. Dietary assessment was made by a 79-item validated food frequency questionnaire. Habitual RSV intakes were estimated as the sum of trans- and cis- isomers of resveratrol and piceid according to the available database. Multivariable conditional logistic regression was applied to examine the relationship of dietary RSV and RSV-rich foods with hip fracture risk. A total of 1,070 pairs of hip fracture incident cases and controls were recruited and 1,065 were included for analysis. Compared with the lowest group, total RSV in the highest quartile group had significantly reduced hip fracture risk by 66.3% (OR: 0.337, 0.222 ~ 0.571, ptrend < 0.001). Similar findings were observed for cis- and trans-RSV, cis- and trans-Piceid, as well as RSV-rich foods (grapes, apples and nuts) respectively. Subgroup analysis suggested more evident findings among female and less obese participants. Our findings demonstrated that higher habitual RSV intakes and RSV-rich foods, even in a relatively low amount, were associated with reduced risk of hip fracture in Chinese elderly.

Efficacy and feasibility of a 12-week Tai Chi training for the prophylaxis of episodic migraine in Hong Kong Chinese women: A randomized controlled trial.

Background: Tai Chi has been broadly applied as alternative treatment for many neurological and psychological disorders. Whereas no study using Tai Chi as prophylactic treatment for migraine. The purpose of this study was to preliminarily examine the efficacy and feasibility of a 12-week Tai Chi training on migraine attack prevention in a sample of Chinese women. Methods: A two-arm randomized controlled trial was designed. Women aged 18 to 65 years and diagnosed with episodic migraine were randomized to either Tai Chi group (TC group) or the waiting list control group. A modified 33-short form Yang-style Tai Chi training with 1 h per day, 5 days per week for 12 weeks was implemented in the TC group, with a 12-week follow up period. The control group received a "delayed" Tai Chi training at the end of the trial. The primary outcome was the differences in attack frequency between 4 weeks before baseline and at the 9-12 weeks after randomization. The intensity and duration of headache were also measured. The feasibility was evaluated by the maintenance of Tai Chi practice and satisfactory level of the participants toward training. Results: Eighty-two women were randomized, finally 40 in TC group and 33 in control group were involved in the analysis. On average, women in TC group had 3.0 times (95% CI: -4.0 to -2.0, P < 0.01) and 3.6 days (95% CI: -4.7 to -2.5, P < 0.01) reduction of migraine attack per month. Compared with the control group, the differences were statistically significant (-3.7 attacks/month, 95% CI: -5.4 to -1.9; and -3.0 migraine days/month, 95% CI: -4.5 to -1.5; both P < 0.001). The intensity and duration of headache had 0.6 (95% CI: -1.2 to -0.0, P < 0.05) units and 1.2 (IQR: -5.0 to 1.1, P < 0.05) hours reduction in TC group, respectively. Most of the participants (69.2%-97.4%) were satisfied with the training. At the end of 24 weeks, on average, the participants maintained 1.5 times of practice per week and 20 min for each practice. Conclusion: The 12-week Tai Chi training significantly decreased the frequency of migraine attack. It was acceptable and practicable among female migraineurs. Clinical trial registration: www.ClinicalTrials.gov, identifier: NCT03015753.

The 6-month effect of whole soy and purified isoflavones daidzein on thyroid function-A double-blind, randomized, placebo controlled trial among Chinese equol-producing postmenopausal women.

The aim of this study was to examine the effect of whole soy and purified daidzein on markers of thyroid function in Chinese postmenopausal women who were equol-producers. Total 270 eligible women were randomized to either one of the three isocaloric supplements: 40 g soy flour (whole soy group), 40 g low-fat milk powder +63 mg daidzein (daidzein group) or 40 g low-fat milk powder (placebo) daily for 6 months. Serum thyroid markers were tested at baseline and 6 months for thyroid stimulating hormone, free triiodothyronine, reverse triiodothyronine and free thyroxine (FT4). There was no significant difference in the 6-month changes of thyroid markers among the three groups. Subgroup analysis among women with lowered thyroid function suggested a modest decrease of FT4. This randomized controlled trial among Chinese equol-producing postmenopausal women indicates the consumption of whole soy and purified daidzein at the provided dosages are safe and have no detrimental effect on thyroid function.

Effect of whole soy and purified daidzein on androgenic hormones in chinese equol-producing post-menopausal women: a six-month randomised, double-blinded and Placebo-Controlled trial.

A randomised, double-blind and placebo-controlled trial was performed to examine the effects of whole soy and isoflavone daidzein on serum androgenic hormones in Chinese equol-producing post-menopausal women. A total of 270 eligible women aged 45-70 years were randomised to either one of the three iso-caloric supplements: 40 g soy flour (whole soy group), 40 g low-fat milk powder +63 mg daidzein (daidzein group) or 40 g low-fat milk powder (placebo group) daily for 6 months. Fasting venous samples were tested for serum androstenedione (AD), testosterone (T), prolactin, sex hormone binding globulin and dehydroepiandrosterone sulphate. Intention-to-treat analysis indicated that serum T (p = .022) and AD (p = .05) levels modestly but significantly decreased after 6-month daidzein treatment in comparison with placebo, with a mean difference of -0.057 nmol/L (95%CI: -0.185 to 0.070, p = .018) and -0.118 ng/mL (95%CI: -0.240-0.004, p = .045), respectively. This 6-month trial suggested that purified daidzein may exhibit less androgenic effect.Trial registration: The trial was registered in ClinicalTrials.gov with identifier of NCT01270737. (URL: http://clinicaltrials.gov/ct2/show/NCT01270737.).

The influence of visual mental imagery size on metamemory accuracy in judgment of learning.

Many studies have found the font size of to-be-remembered words has a significant influence on judgments of learning (JOLs). However, few studies have investigated whether JOLs are affected by the mental imagery size of to-be-remembered words, even when the font sizes themselves are kept identical in study materials. This study investigated whether the visual mental imagery size influences the participants' JOLs and what the underlying mechanisms are. In Experiments 1 and 2, participants learned words with identical font sizes, mentally generated large or small imageries and then made JOLs. We found that JOLs under the large imagery condition were significantly higher than those under the small imagery condition, but actual recall performance exhibited no significant difference. In Experiment 3, participants pressed a button immediately after mental imagery generation and showed that it took significantly longer to generate large imageries than to generate small imageries, and the difference in JOLs between two conditions was no longer significant. In Experiment 4, we used a questionnaire to investigate the contribution of beliefs and found that participants believed large imageries were easier to remember. These findings indicate that imagery size has a significant impact on JOLs, in which beliefs may play a leading role.

Research protocol: effect of natural S-equol on blood pressure and vascular function--a six-month randomized controlled trial among equol non-producers of postmenopausal women with prehypertension or untreated stage 1 hypertension.

BACKGROUND: Although higher habitual soy intake is associated with lower blood pressure (BP) and stroke incidence, clinical trials using soy protein or isoflavones on cardiovascular risks yielded inconsistent results. The discrepancies are hypothesized to be due to the individuals' intestinal bacterial capacity to metabolite isoflavones daidzein into equol. Animal and in vitro studies have revealed that equol has stronger estrogen-like and anti-oxidative activity than isoflavones and possesses natriuretic and vasorelaxant properties which may play an important role in the prevention of hypertension. However, no clinical trial has examined the effect of equol on BP. We thus propose a 24-week randomized controlled trial to test the effectiveness of natural S-equol on BP and vascular function among equol non-producers. METHODS/DESIGN: This will be a 6-month double-blind, randomized, placebo-controlled trial among 207 non-equol producing postmenopausal women with prehypertension or early untreated hypertension. Eligible participants who have completed a 2-week run-in will be randomized to either one of the 3 groups: placebo group, low-equol group (10 mg/d) and high equol group (20 mg/d). The outcome measures will be conducted at baseline and at the end of the trial including 24 h ambulatory BP, endothelial function (by ultrasound determined brachial flow mediated dilation), arterial stiffness (by pulse wave analysis) and other cardiovascular risk factors (lipid profile, glycemic control and inflammatory biomarkers). Urinary isoflavones will be tested for compliance assessment. One way analysis of variance will be applied to compare the 6-month changes in ambulatory BP or parameters of vascular function among the 3 treatment groups. DISCUSSION: This study will be performed in community subjects. If the antihypertensive effect of equol is proven, the provision of natural equol to those high risk adults who are unable to produce equol will have enormous public health implications for the primary and secondary prevention of hypertension and cardiovascular diseases on a population basis. The research efforts will also have significant implications for industry in the provision of suitable soy products for the prevention of hypertension and its related complications. TRIAL REGISTRATION: The trial was registered in ClinicalTrials.gov with identifier of NCT02515682 .

Effect of whole soy and purified isoflavone daidzein on renal function--a 6-month randomized controlled trial in equol-producing postmenopausal women with prehypertension.

OBJECTIVES: The aim of the study was to examine the long-term effect of commonly used whole soy foods (soy flour) and purified daidzein (one major isoflavone and the precursor of equol) on renal function among prehypertensive postmenopausal women who are also equol producers, a population most likely to benefit from soy intervention. DESIGN AND METHODS: This was a 6-month double-blind, randomized, placebo-controlled trial. Two hundred seventy eligible Chinese women were randomized to either one of the three treatments: 40 g soy flour (whole soy group), 40 g low-fat milk powder + 63 mg daidzein (daidzein group) or 40 g low-fat milk powder (placebo group) daily each for 6 months. Fasting blood and 24-h urine samples were collected at the beginning and end of trial. Serum creatinine, cystatin C, urea, angiotensin-converting enzyme, minerals and 24-h urinary creatinine and minerals were analyzed. Estimated glomerular filtration rate (eGFR) was calculated with the Cockcroft-Gault and the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equations. RESULTS: Two hundred fifty-three subjects completed the study according to the protocol. Urinary isoflavones indicated good compliance of participants. No significant changes were observed in most of renal parameters, however, there was a less decrease in eGFRcockcroft in 6-month change (p=0.044) and %change (p=0.031) with whole soy intake relative to milk placebo. Subgroup analysis among women with lowered renal function suggested whole soy consumption tended to improve markers of renal function relative to control. CONCLUSIONS: Six-month consumption of whole soy tended to have a modest improvement of renal function in prehypertensive postmenopausal women with lowered renal function. Future trials in subjects with more declined renal function are necessary. TRIAL REGISTRATION: The trial was registered in ClinicalTrials.gov with identifier of NCT01270737. (URL: http://clinicaltrials.gov/ct2/show/NCT01270737).

Randomized controlled trial of whole soy and isoflavone daidzein on menopausal symptoms in equol-producing Chinese postmenopausal women.

OBJECTIVE: Dietary supplements containing soy or isoflavones are widely used as alternatives to hormone therapy. However, their efficacy is still inconclusive, and limited data on equol producers are available. The aim of this study was to examine the effect of whole soy (soy flour) or purified daidzein (one major soy isoflavone and the precursor of equol) on menopausal symptoms in equol-producing postmenopausal women, a population most likely to benefit from soy intervention. METHODS: This is a 6-month parallel-group, double-blind, randomized, placebo-controlled trial. Two hundred seventy equol-producing prehypertensive Chinese postmenopausal women were randomized to one of three treatment groups: 40 g of soy flour (whole soy group), 40 g of low-fat milk powder + 63 mg of daidzein (daidzein group), or 40 g of low-fat milk powder (placebo group) daily, each given as a solid beverage for 6 months. Changes in menopausal symptoms were assessed by a validated and structured symptom checklist at baseline and 6 months. RESULTS: Two hundred fifty-three participants completed the study according to protocol. Urinary isoflavones indicated good compliance with the interventions. Baseline menopausal symptoms were comparable among the three study groups. Intention-to-treat analysis indicated that there was no significant difference in the 6-month changes or percent changes in the total number of menopausal symptoms, in the five dimensions of symptoms, and in the frequencies of individual symptoms among the three treatment groups. CONCLUSIONS: Whole soy and purified daidzein have no significant effect on alleviation of menopausal symptoms among equol-producing postmenopausal women with prehypertension.

Whole soy, but not purified daidzein, had a favorable effect on improvement of cardiovascular risks: a 6-month randomized, double-blind, and placebo-controlled trial in equol-producing postmenopausal women.

SCOPE: Equol is produced by the intestinal bacteria from isoflavone daidzein. Studies have reported the health benefits of soy can only present or more pronounced in equol producers. This 6-month randomized controlled trial examined the effect of whole soy (soy flour) and purified daidzein on cardiovascular biomarkers and carotid intima-media thickness (CIMT) in prehypertensive postmenopausal women who were equol producers. METHODS AND RESULTS: Two hundred seventy eligible women were randomized to either one of the three treatments: 40 g soy flour (whole soy group), 40 g low-fat milk powder + 63 mg daidzein (daidzein group), or 40 g low-fat milk powder (placebo group) daily each for 6 months. Fasting venous samples were obtained at baseline and end of trial for testing glucose, lipids, high sensitivity C-reactive protein (hs-CRP), and free fatty acid. Changes in common CIMT were also assessed. Serum LDL-C decreased by 7.95% (95% CI: -15.09∼-0.81%) and 6.32% (95% CI: -13.45∼0.08%), and serum hs-CRP decreased by 0.164 (95% CI: -0.309∼-0.019) and 0.054 (95% CI: -0.199∼0.012) in the whole soy group compared with daidzein and milk placebo groups, respectively. No significant change in CIMT was found. CONCLUSION: Whole soy, but not purified daidzein, had a beneficial effect on reduction of LDL-C and hs-CRP among prehypertensive equol-producing postmenopausal women.

A six-month randomized controlled trial of whole soy and isoflavones daidzein on body composition in equol-producing postmenopausal women with prehypertension.

OBJECTIVES: This paper reported the effects of commonly used whole soy foods (soy flour) and purified daidzein (one of the major isoflavones and the precursor of equol) on changes in anthropometric measurements and body composition in a 6-month double-blind, randomized, placebo-controlled trial among prehypertensive postmenopausal women who are also equol producers. METHODS: 270 eligible women were randomized to either one of the three treatments: 40 g soy flour (whole soy group), 40 g low-fat milk powder + 63 mg daidzein (daidzein group), or 40 g low-fat milk powder (placebo group) daily each for 6 months. Anthropometric indicators and body composition were measured before and after intervention. RESULTS: 253 subjects completed the study with good compliance. Urinary isoflavones levels suggested good compliance of subjects with supplementation. Whole soy and purified daidzein had no significant effect on body weight, body mass index (BMI), waist and hip circumferences, waist to hip ratio (WHR), body fat percentage, fat mass, and free fat mass. CONCLUSION: Six-month consumption of whole soy and purified daidzein at provided dosage had no improvement on body weight and composition compared with isocaloric milk placebo among prehypertensive equol-producing postmenopausal women. This trial is registered with ClinicalTrials.gov NCT01270737.

The role of vitamin D in blood pressure, endothelial and renal function in postmenopausal women.

BACKGROUND: Vitamin D is a pro-hormone that plays an essential role in the vasculature and in kidney function. AIMS: To review the extra-skeletal effects of vitamin D on blood pressure, endothelial and renal function with emphasis on recent findings in postmenopausal women. METHODS: Included in this review was a PubMed database search for English language articles through March 2013. This review discussed the physiology and definition of vitamin D deficiency, the recent evidence for the role vitamin D in blood pressure, vascular and renal function. RESULTS: Experimental and epidemiological data suggest that vitamin D plays an important role in the vasculature and in kidney function. Low vitamin D concentrations appear to significantly associate with hypertension, endothelial and renal dysfunction. However, the results of clinical trials have generally been mixed. Studies specifically conducted among postmenopausal women are limited and findings are still inconsistent. CONCLUSIONS: Definitive studies are warranted to elucidate the effects of vitamin D supplementation on vascular and renal function and a more detailed work is needed to outline the route, duration and optimal dose of supplementation. It is premature to recommend vitamin D as a therapeutic option in the improvement of vascular and renal function at the current stage.

Effects of soy protein and isoflavones on glycemic control and insulin sensitivity: a 6-mo double-blind, randomized, placebo-controlled trial in postmenopausal Chinese women with prediabetes or untreated early diabetes.

BACKGROUND: In vitro and animal studies have suggested that soy protein and isoflavones have favorable effects on glucose and insulin regulation, but intervention studies in humans are limited, and the results are controversial. OBJECTIVE: We investigated whether soy protein with isoflavones and soy isoflavone extracts could improve glycemic control and insulin sensitivity in postmenopausal women with early hyperglycemia. DESIGN: This was a randomized, double-blind, placebo-controlled trial that included 180 postmenopausal Hong Kong Chinese women with prediabetes or early untreated diabetes. After a 2-wk adaptation period, participants were randomly assigned to 1 of 3 arms to receive 15 g soy protein and 100 mg isoflavones, 15 g milk protein and 100 mg isoflavones, or 15 g milk protein on a daily basis for 6 mo. RESULTS: Three- or 6-mo treatments with soy protein with or without isoflavone supplementation did not result in favorable changes in the descriptors for glycemic control and insulin resistance, namely fasting and 2-h postload glucose, fasting and postload insulin, glycated serum protein, and homeostasis model assessment for insulin resistance and beta-cell function. CONCLUSIONS: This 6-mo randomized controlled trial did not support the hypothesis that soy protein with or without isoflavone supplementation had favorable effects on glycemic control and insulin sensitivity among postmenopausal Chinese women. The favorable change in postload glucose needs to be further confirmed.