Explore the vast range of titles available.

The coronavirus disease (COVID-19) has led to an rush to repurpose existing drugs, although the underlying evidence base is of variable quality. Drug repurposing is a technique by taking advantage of existing known drugs or drug combinations to be explored in an unexpected medical scenario. Drug repurposing, hence, plays a vital role in accelerating the pre-clinical process of designing novel drugs by saving time and cost compared to the traditional de novo drug discovery processes. Since drug repurposing depends on massive observed data from existing drugs and diseases, the tremendous growth of publicly available large-scale machine learning methods supplies the state-of-the-art application of data science to signaling disease, medicine, therapeutics, and identifying targets with the least error. In this article, we introduce guidelines on strategies and options of utilizing machine learning approaches for accelerating drug repurposing. We discuss how to employ machine learning methods in studying precision medicine, and as an instance, how machine learning approaches can accelerate COVID-19 drug repurposing by developing Chinese traditional medicine therapy. This article provides a strong reasonableness for employing machine learning methods for drug repurposing, including during fighting for COVID-19 pandemic.

(1) Background: Macrosomia is prevalent in China and worldwide. The current method of predicting macrosomia is ultrasonography. We aimed to develop new predictive models for recognizing macrosomia using a random forest model to improve the sensitivity and specificity of macrosomia prediction; (2) Methods: Based on the Shandong Multi-Center Healthcare Big Data Platform, we collected the prenatal examination and delivery data from June 2017 to May 2018 in Jinan, including the macrosomia and normal-weight newborns. We constructed a random forest model and a logistic regression model for predicting macrosomia. We compared the validity and predictive value of these two methods and the traditional method; (3) Results: 405 macrosomia cases and 3855 normal-weight newborns fit the selection criteria and 405 pairs of macrosomia and control cases were brought into the random forest model and logistic regression model. On the basis of the average decrease of the Gini coefficient, the order of influencing factors was: interspinal diameter, transverse outlet, intercristal diameter, sacral external diameter, pre-pregnancy body mass index, age, the number of pregnancies, and the parity. The sensitivity, specificity, and area under curve were 91.7%, 91.7%, and 95.3% for the random forest model, and 56.2%, 82.6%, and 72.0% for logistic regression model, respectively; the sensitivity and specificity were 29.6% and 97.5% for the ultrasound; (4) Conclusions: A random forest model based on the maternal information can be used to predict macrosomia accurately during pregnancy, which provides a scientific basis for developing rapid screening and diagnosis tools for macrosomia.

We developed a model to predict the quality of fresh goji berries during storage by analyzing the correlations of their dielectric properties. The variations in these properties with storage temperature, time, and frequency were systematically characterized to inform the model. Leveraging these relationships, we developed a model to predict quality. The analysis integrated measurements of dielectric properties with assessments of texture and key physicochemical indicators. Results indicate that dielectric parameters exhibit significant frequency dependence. Complex impedance (Z), capacitance (Cp), and resistance (Rp) all decreased sharply with increasing frequency, with the most pronounced change observed in Cp. Conductance, G, and reactance, X, increased with frequency, reaching maximum increases of 360.86% and 87.79%, respectively. Under the specific test frequency of 163,280 Hz, a strong polynomial relationship was observed between the dielectric parameters and storage time, with all fitted models yielding Radj2 values above 0.94. The quality factor Q (a dimensionless number for the energy efficiency of a resonant circuit or medium) showed a near-perfect correlation with brittleness, while reactance, X, was correlated with springiness and cohesiveness, with correlation coefficients approaching 0.999 under the optimal test frequency. The constructed ANN model demonstrated high prediction accuracy for hardness, brittleness, elasticity, cohesiveness, chewiness, and soluble solids content (R2 > 0.97, MSE < 5%) but performed poorly in predicting adhesiveness, stickiness, and rebound elasticity (R2 < 0.9). The constructed LSSVM model showed good prediction performance for some indicators (hardness, springiness, cohesiveness, and SSC) (R2 > 0.94), but its prediction accuracy was low for brittleness and chewiness (R2 < 0.9). Overall, its performance and generalization ability were inferior to the ANN model. This study shows that ANN models based on dielectric properties establish a technical foundation for the non-destructive, automated monitoring of goji berry storage quality, thereby providing a critical tool for dynamic quality tracking and value assessment within integrated warehouse management systems.

Introduction Tiered social health insurance (SHI) schemes exist in many countries and may lead to significant disparities of healthcare and financial protection. The degree of cancer care inequalities under tiered SHI in China and other low- and middle-income countries (LMICs) remain poorly understood. Methods We obtained hospital discharged summary for 319,677 patients diagnosed with lung cancer between 2017 and 2021 in Shandong, China, and established propensity score-matched samples under the Urban and Rural Resident Basic Medical Insurance (URRBMI) and those under the Urban Employee Basic Medical Insurance (UEBMI). We ran multivariable regressions to assess the effects of SHI schemes on cancer treatment and expenditures. Subgroup analyses of cancer treatment were conducted based on whether the cancer had metastasized. Results In the matched samples, utilization of inpatient cancer care increased under both schemes from 2017 to 2021. Higher proportions of inpatient cancer care utilization were seen in those under UEBMI compared those under URRBMI, consistently with statistical significance. UEBMI was associated with a higher probability of receiving surgery in patients without metastasis, and higher probabilities of receiving radiotherapy or chemotherapy, targeted therapy, and immunotherapy in patients with metastasis. Patients under UEBMI were also less likely to be discharged against medical advice than those under URRBMI. Furthermore, UEBMI beneficiaries had 13.3% higher total expenditures but 19.1% lower out-of-pocket expenditures. Conclusions Significant gaps remained in access to inpatient treatment and financial protection for lung cancer, particularly in surgery for non-metastatic cancer. Targeted harmonization of benefit packages is needed to address pressing disparities in cancer care in LMICs with tiered SHI.

Background Studies have demonstrated that high or low haemoglobin increases the risk of stroke. Previous studies, however, performed only a limited number of haemoglobin measurements, while there are dynamic haemoglobin changes over the course of a lifetime. This longitudinal cohort study aimed to classify the long-term trajectory of haemoglobin and examine its association with stroke incidence. Methods The cohort consisted of 11,431 participants (6549 men) aged 20 to 50 years whose haemoglobin was repeatedly measured 3–9 times during 2004–2015. A latent class growth mixture model (LCGMM) was used to classify the long-term trajectory of haemoglobin concentrations, and hazard ratios (HRs) and 95% confidence intervals (95% CI) according to the Cox proportional hazard model were used to investigate the association of haemoglobin trajectory types with the risk of stroke. Results Three distinct trajectory types, high-stable ( n  = 5395), normal-stable ( n  = 5310), and decreasing ( n  = 726), were identified, with stroke incidence rates of 2.7, 1.9 and 3.2 per 1000 person-years, respectively. Compared to the normal-stable group, after adjusting for the baseline covariates, the decreasing group had a 2.94-fold (95% CI 1.22 to 7.06) increased risk of developing stroke. Strong evidence was observed in men, with an HR (95% CI) of 4.12 (1.50, 11.28), but not in women (HR = 1.66, 95% CI 0.34, 8.19). Individuals in the high-stable group had increased values of baseline covariates, but the adjusted HR (95% CI), at 1.23 (0.77, 1.97), was not significant for the study cohort or for men and women separately. Conclusions This study revealed that a decreasing haemoglobin trajectory was associated with an increased risk of stroke in men. These findings suggest that long-term decreasing haemoglobin levels might increase the risk of stroke.

Background Limited studies have compared the association between various physical measurements and the risk of cancer or cardiovascular disease (CVD). We aim to explore the best‐individualized indicators of cancer and CVD risk assessment. Methods From May 2004 to December 2017, a community‐based cohort in China involving 100 280 participants were enrolled. BMI, height, body surface area (BSA), and body fat percentage (BFP) were compared in parallel about cancer and CVD risk with the multivariable‐adjusted Cox proportional hazard regression model. Results Within the follow‐up period, 3107 (3.10%) were diagnosed with cancer and 3721 (3.71%) had CVD. Per‐level increased (in tertile: T1, T2, and T3 level) BSA, height, and BFP was positively associated with the risk of overall cancer [HR (95% CI): 1.10 (1.05‐1.15), 1.12 (1.07‐1.18), and 1.10 (1.03‐1.16), respectively], whereas BMI was insignificant. Compared with the reference group (T2), the highest BSA level (T3) was positively associated with overall cancer incidence for both male [HR (95% CI): 1.28 (1.13‐1.45)] and female [HR (95% CI): 1.13 (1.00‐1.28)]. The BSA, height, and BFP also significantly associated with some site‐specific cancers including thyroid, stomach, breast, urinary system, and skin cancer. Meanwhile, BFP presented a strong positive association with overall CVD [HR (95% CI): 1.22 (1.15‐1.30) in trend] in both gender and associated with nearly all CVD subtypes especially the myocardial infarction and heart failure. Conclusion BSA, height, and BFP have more sensitivity in assessing cancer risk and BFP shows the largest hazard ratios for CVD incident. We provided valuable evidence for the application of height, BSA, and BFP in routine healthcare practice. These encouraging findings should be tested in more well‐defined studies for risk prediction. Body surface area, height, and body fat percentage has higher sensitivity in assessing cancer risk than BMI. Body fat percentage shows the largest hazard ratios in all cardiovascular events. BSA, height, and BFP have considerable application value in routine healthcare practice.

Background The relative contributions of genetic and environmental factors versus unavoidable stochastic risk factors to the variation in cancer risk among tissues have become a widely-discussed topic. Some claim that the stochastic effects of DNA replication are mainly responsible, others believe that cancer risk is heavily affected by environmental and hereditary factors. Some of these studies made evidence from the correlation analysis between the lifetime number of stem cell divisions within each tissue and tissue-specific lifetime cancer risk. However, they did not consider the measurement error in the estimated number of stem cell divisions, which is caused by the exposure to different levels of genetic and environmental factors. This will obscure the authentic contribution of environmental or inherited factors. Methods In this study, we proposed two distinct modeling strategies, which integrate the measurement error model with the prevailing model of carcinogenesis to quantitatively evaluate the contribution of hereditary and environmental factors to cancer development. Then, we applied the proposed strategies to cancer data from 423 registries in 68 different countries (global-wide), 125 registries across China (national-wide of China), and 139 counties in Shandong province (Shandong provincial, China), respectively. Results The results suggest that the contribution of genetic and environmental factors is at least 92% to the variation in cancer risk among 17 tissues. Moreover, mutations occurring in progenitor cells and differentiated cells are less likely to be accumulated enough for cancer to occur, and the carcinogenesis is more likely to originate from stem cells. Except for medulloblastoma, the contribution of genetic and environmental factors to the risk of other 16 organ-specific cancers are all more than 60%. Conclusions This work provides additional evidence that genetic and environmental factors play leading roles in cancer development. Therefore, the identification of modifiable environmental and hereditary risk factors for each cancer is highly recommended, and primary prevention in early life-course should be the major focus of cancer prevention.

PurposeThe population-based Kongcun Town Asymptomatic Intracranial Artery Stenosis (KT-aICAS) study aims to investigate the prevalence of aICAS and major cardiovascular risk factors (CRFs) or biomarkers related to the development and prognosis of aICAS.ParticipantsThe KT-aICAS study included 2311 rural residents who were aged ≥40 years and living in Kongcun Town, Shandong Province, China. Baseline examination was conducted from October 2017 to October 2018, during which information on demographics, socioeconomics, personal and family medical history, and lifestyle factors was collected through face-to-face interviews, physical examination and blood tests. aICAS was initially screened using transcranial Doppler examination and then diagnosed using magnetic resonance angiography. Atherosclerosis in carotid arteries was diagnosed via carotid ultrasonography. High-resolution MRI was further used to evaluate the vessel wall of aICAS. Neuropsychological assessments were performed in the participants diagnosed with aICAS and the age-matched and sex-matched controls.Findings to dateOf the 2311 participants, 2027 (87.7%) completed the diagnostic procedure and aICAS was detected in 154 persons, resulting in an overall prevalence of 7.6%. The prevalence of aICAS increased with advancing age from 5.1% in participants aged 40–49 years to 12.7% in those aged ≥70 years (p<0.001). aICAS was detected in 305 intracranial arteries, including 221 (72.5%) in the anterior circulation and 84 (27.5%) in the posterior circulation (p<0.001). In addition, major CRFs were highly prevalent among middle-aged and elderly rural dwellers who were free of clinical stroke.Future plansFollow-up examinations will be performed every 3 years following the baseline examination. This study will increase our knowledge about the natural history of aICAS and facilitate studies of aICAS-associated disorders among rural-dwelling Chinese adults, such as ischaemic stroke and vascular cognitive impairment.Trial registration numberChiCTR1800017197.

Despite rapid development, cancer registries in low- and middle-income countries, such as China, have the persistent problems with up to 6-year delay and a lack of reported details about small areas. This study aimed to develop an approach to provide more up-to-date localized cancer surveillance using linked administrative data. We used lung cancer as an example. Based on data of hospitalization record front pages (HRFPs) between 2013 and 2022 from all the secondary and tertiary hospitals in Shandong Province, China, we identified incident cases of lung cancer in 2022 with 2013-2021 being the washout period. Deaths from lung cancer were ascertained for 2022 using linked HRFPs and death registration data. We estimated age-standardized incidence and mortality rates (ASIR and ASMR) of lung cancer in 2022 using Segi world standard population, age-specific incidence and mortality rates by sex, and county-level ASIR and ASMR to illustrate regional disparity. We grouped the counties by municipalities and calculated the Theil indices for within-municipality inequality and between-municipality inequality. The HRFPs captured 79,672 incident cases of lung cancer in Shandong in 2022 (45,527 males, 34,145 females). The ASIR of lung cancer in Shandong was 42.46 per 100,000 in both sexes (49.19/100,000 in males vs 36.67/100,000 in females). A total of 40,626 lung cancer-specific deaths were ascertained (28,185 men and 12,441 women). The ASMR was 19.76/100,000 in both sexes, 26.29/100,000 and 11.38/100,000 in males and females, respectively. The IQR of county-level ASIR and ASMR were 17.13/100,000 and 10.41/100,000, respectively. The inequality was primarily due to within-municipality disparities, with within-municipality Theil T indices higher than between-municipality Theil T indices (0.0572 vs 0.0033 for ASIR, 0.0824 vs 0.0011 for ASMR). The cancer surveillance approach based on linked administrative data could provide up-to-date small-area estimates of cancer burden, when cancer registry data are not yet reported and for areas not covered by cancer registries. It could reveal disparity of cancer epidemiology, which provides leads for further investigation into the underlying causes and potential solutions for equity improvement.

IntroductionThe effects of bilirubin on asymptomatic intracranial atherosclerosis (aICAS) remain uncertain.ObjectivesTo investigate the association between bilirubin and aICAS in rural-dwelling Chinese people.MethodsThis population-based study included 2013 participants from the Kongcun Town Study, which aimed to investigate the prevalence of aICAS in people aged ≥ 40 years who were free of stroke and hepatic and gall disease history. Baseline data were collected via interviews, clinical examinations, and laboratory tests. Total bilirubin (Tbil), direct bilirubin (Dbil), and indirect bilirubin (Ibil) levels were divided into high-concentration group and low-concentration group, respectively. We diagnosed aICAS and moderate-to-severe aICAS (m-saICAS) (≥ 50% stenosis) by integrating transcranial Doppler ultrasound with magnetic resonance angiography. The association between bilirubin and aICAS, as well as m-saICAS, was analyzed using logistic regression.ResultsOf the 2013 participants, those in the high-concentration group of Tbil (odds ratio (OR), 0.50; 95% confidence interval (CI), 0.42–0.87), Dbil (OR 0.60, 95%CI 0.41–0.87), and Ibil (OR 0.67; 95%CI 0.47–0.97) had a lower risk of aICAS than those in the low-concentration group after adjusting all confounders. The high concentrations of Tbil, Dbil, and Ibil were also negatively associated with m-saICAS. After stratification according to age, Tbil, Dbil, and Ibil were significantly negatively associated with aICAS among participants aged ≥ 60 years.ConclusionTbil, Dbil, and Ibil might be independent protective factors for aICAS and moderate-to-severe aICAS in rural-dwelling Chinese people, especially among older participants aged ≥ 60 years.