The Lancet Regional Health: Western Pacific最新文献

Strategies for the prevention of ischemic stroke in atrial fibrillation in East Asia: clinical features, changes and challenges

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-15 DOI: 10.1016/j.lanwpc.2025.101495

Tze-Fan Chao , Eue-Keun Choi , Yutao Guo , Wataru Shimizu , Hung-Fat Tse , Gregory Y.H. Lip

引用次数: 0

National Thalassemia Registry: a 30 year journey of implementing carrier screening in Singapore

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2025.101471

Stella Zhang , Guek Peng Tan , Soh Lan Peh , Swee Lim Ang , Sylvia Kam , Weng Khong Lim , Teck Wah Ting , Angeline Lai , Ee Shien Tan , Saumya Shekhar Jamuar , Hai Yang Law , Ivy Ng

引用次数: 0

Prevalence and temporal trends in myopia and high myopia children in China: a systematic review and meta-analysis with projections from 2020 to 2050

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2025.101484

Wei Pan , Seang-Mei Saw , Tien Yin Wong , Ian Morgan , Zhikuan Yang , Weizhong Lan

{"title":"Prevalence and temporal trends in myopia and high myopia children in China: a systematic review and meta-analysis with projections from 2020 to 2050","authors":"Wei Pan , Seang-Mei Saw , Tien Yin Wong , Ian Morgan , Zhikuan Yang , Weizhong Lan","doi":"10.1016/j.lanwpc.2025.101484","DOIUrl":"10.1016/j.lanwpc.2025.101484","url":null,"abstract":"<div><h3>Background</h3><div>Myopia rates have risen in the past decades in China. New strategies for the prevention and control of myopia are now available, and understanding the prevalence and future trends in myopia and high myopia in children and adolescents in China may provide insights into the impact of implementing these measures. The study aims to provide updated data on the prevalence of myopia and high myopia in children and to project temporal trends in prevalence from 2020 to 2050 in China.</div></div><div><h3>Methods</h3><div>A systematic review and meta-analysis searching several databases in both English and Chinese: PubMed, Web of Science, Science Direct, China National Knowledge Infrastructure (CNKI), Wanfang, China Science and Technology Journal Database (CSTJ) with date limits from 01/01/2010 to 11/23/2024 was conducted. We included population-based or school-based studies in China that determined the myopia prevalence, based on the cycloplegic refraction, in children under 20. Studies with a response rate <70% or sample size <200 were excluded. A fixed-effect meta-analysis was used, and projections were made based on three scenarios: experience-based, maximum growth (maximum near-work, minimal outdoor time), and minimum growth (2 h outdoor time daily).</div></div><div><h3>Findings</h3><div>From 6555 reports, 82 studies with 218,794 participants were included. The overall myopia prevalence was 36.6% (95% CI: 36.4%, 36.8%), with rates of 2.6% in ages 0–4, 22.0% in ages 5–9, 45.4% in ages 10–14, and 67.2% in ages 15–19. High myopia prevalence was 5.3% overall, with rates of 0.1% in ages 0–4, 1.1% in ages 5–9, 3.0% in ages 10–14, and 9.5% in ages 15–19. Projections for 2030 under minimum growth, experience-based, and maximum growth scenarios were 26.8%, 46.2%, 56.0%; 2040 were 19.6%, 54.4%, 65.6%; and 2050 were 14.4%, 61.3%, 71.9%, respectively.</div></div><div><h3>Interpretation</h3><div>China is facing a substantial and potentially worsening epidemic of childhood myopia. This information will provide data for guiding implementation and evaluating the effectiveness of existing and new nationwide myopia prevention and control programs.</div></div><div><h3>Funding</h3><div>The <span>Science and Technology Innovation Program</span> of Hunan Province, China (2023RC1079, 2024RC5002).</div></div>","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101484"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143178053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Middle-age cerebral small vessel disease and cognitive function in later life: a population-based prospective cohort study

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2024.101284

Ali Tanweer Siddiquee , Yoon Ho Hwang , Soriul Kim , Sung Jin Shin , Ji Soo Lee , June Christoph Kang , Min-Hee Lee , Hyeon Jin Kim , Seung Ku Lee , Chol Shin

{"title":"Middle-age cerebral small vessel disease and cognitive function in later life: a population-based prospective cohort study","authors":"Ali Tanweer Siddiquee , Yoon Ho Hwang , Soriul Kim , Sung Jin Shin , Ji Soo Lee , June Christoph Kang , Min-Hee Lee , Hyeon Jin Kim , Seung Ku Lee , Chol Shin","doi":"10.1016/j.lanwpc.2024.101284","DOIUrl":"10.1016/j.lanwpc.2024.101284","url":null,"abstract":"<div><h3>Background</h3><div>Cerebral small vessel disease (cSVD) is a major pathologic substrate of vascular contribution to cognitive impairment. However, population based long-term longitudinal cognitive function data in relation to cSVD are rare. We investigated the relationship between cSVD and cognitive decline over time in middle-aged through elderly population.</div></div><div><h3>Methods</h3><div>This prospective cohort study was conducted in a community-based adult population (avg. age 58.5 ± 6.4) who underwent both magnetic resonance imaging (MRI) and comprehensive neuropsychological tests at baseline (2011–2014). The participants were followed-up with the same neuropsychological test battery 4-yearly in two more cycles (in 2015–2018 and 2019–2022). A total of 2454 participants who were free of dementia and cerebrovascular disease at baseline with cognitive function testing at least 2 time points over the time were analyzed. Data analysis was performed from May 1, 2023 to January 31, 2024. SVD was defined by the presence of any of the visible MRI markers (age-related white matter change, lacunes and cerebral microbleeds) at baseline. The main outcomes were multivariable adjusted mean differences of cognitive test performances by cSVD groups over time. The neuropsychological assessment battery included verbal and visual memory, verbal fluency, Digit Symbol–coding, Trail Making Test–A, and Stroop Test. To examine the relationship between cSVD and cognitive function, we used linear mixed model for repeated measurements to compare the means (95% CIs) by cSVD groups.</div></div><div><h3>Findings</h3><div>Of the total, 908 (37.0%) participants had cSVD on MRI reading at baseline. By location, cSVD were mostly found in the frontal lobe followed by basal ganglia area of the brain. None of the cognitive test scores, except Trail Making Test–A, were significantly different between the cSVD groups at baseline. At 8-year follow-up, participants without cSVD performed significantly better than participants with cSVD in Stroop–color reading [Mean difference 1.19 (95% CI: 0.02–2.36), p = 0.0451] and visual reproduction-recognition [Mean difference 0.11 (95% CI: 0.01–0.21), p = 0.0221]. While no other cognitive tests showed any differential changes by cSVD groups, logical memory (Story Recall Tests) increased and Stroop-word reading decreased over time in both cSVD groups almost identically.</div></div><div><h3>Interpretation</h3><div>Silent cSVD was independently associated with decline in executive functioning over 8-year follow-up period in this Korean middle-aged through elderly general population. Future studies considering wider spectrum of cSVD and longer follow-up durations may help predict further cognitive outcomes.</div></div><div><h3>Funding</h3><div>This study was funded by the <span>Korea Centers for Disease Control and Prevention</span>.</div></div>","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101284"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787597/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143081101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trends in mortality for gastric cancer from 2011 to 2020 with prediction to 2030: a Bayesian age-period-cohort analysis

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2024.101298

Zhe Liu, Peng Yin

{"title":"Trends in mortality for gastric cancer from 2011 to 2020 with prediction to 2030: a Bayesian age-period-cohort analysis","authors":"Zhe Liu, Peng Yin","doi":"10.1016/j.lanwpc.2024.101298","DOIUrl":"10.1016/j.lanwpc.2024.101298","url":null,"abstract":"<div><h3>Background</h3><div>Gastric cancer was the 3rd most common cause of cancer deaths, accounting for 11.3% of all cancer deaths in China in 2018. The study aims to analyze trends in gastric cancer mortality in China from 2011 to 2020, and predict the future burden of gastric cancer from 2021 to 2030.</div></div><div><h3>Methods</h3><div>Relevant data on gastric cancer were obtained from the National Mortality Surveillance System, which is available from the Chinese Center for Disease Control and Prevention. All deaths with underlying cause of death as gastric cancer (International Classification of Diseases-10 code: C16) were included. We analyzed the numbers and age-standardized mortality rates (ASMR) for gastric cancer by sex and urbanicity in China during 2011-2020. A Bayesian age-period-cohort (BAPC) prediction model was used to predict gastric cancer mortality by sex and urbanicity in China from 2021 to 2030. The gastric cancer death data from 2011 to 2020 were categorized into five-year age groups, from 0-4 to 80+. Population data for 2011-2020 were obtained from the National Bureau of Statistics. Projected population data for 2021-2030 were based on estimates derived from 2011-2020 population. The standard population for calculating ASMR was derived from the China Census in 2020.</div></div><div><h3>Findings</h3><div>In 2020, the ASMR for gastric cancer was 22.24/100,000, accounting for 291.20 thousand deaths in China, including 199.66 thousand males and 91.53 thousand females. The ASMR in males (32.57/100,000) was higher than that in females (13.09/100,000). From 2011 to 2020, the number of gastric cancer deaths in China showed a gradual downward trend, with a notable decline in the ASMR. From 2021 to 2030, the ASMR for gastric cancer in China is expected to continue declining. In 2030, It is anticipated that the ASMR of gastric cancer in China will be 11.68/100,000, resulting in an estimated 218.93 thousand deaths. The ASMR for males is projected to decrease to 17.78/100,000, representing a 45.4% reduction from 2020. For females, the ASMR will decrease to 6.81/100,000 corresponding to a significant reduction of 48.0% from the 2020. In 2030, the projected ASMR for gastric cancer is 11.67/100,000 in urban areas and 12.04/100,000 in rural areas, accounting for 111.90 thousand and 125.92 thousand deaths, respectively. Compared to 2020, the ASMR for gastric cancer in 2030 shows a 38.7% and 50.9% reduction in urban and rural areas, respectively.</div></div><div><h3>Interpretation</h3><div>From 2011 to 2020, both the number of deaths and the ASMR of gastric cancer in China gradually declined. The number of gastric cancer deaths in China is projected to continue declining through 2030. The findings indicate that the preventive and control measures for gastric cancer are effective and may provide useful reference for development of preventive and control strategies for other major cancers in China.</div></div>","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101298"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using machine learning algorithms to predict colorectal cancer

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2024.101355

Xingjian Xiao , Bo Hong , Kubra Maqsood , Xiaohan Yi , Guoqun Xie , Hailei Zhao , Bo Sun , Jianying Mao , Shiyou Liu , Xianglong Xu

{"title":"Using machine learning algorithms to predict colorectal cancer","authors":"Xingjian Xiao , Bo Hong , Kubra Maqsood , Xiaohan Yi , Guoqun Xie , Hailei Zhao , Bo Sun , Jianying Mao , Shiyou Liu , Xianglong Xu","doi":"10.1016/j.lanwpc.2024.101355","DOIUrl":"10.1016/j.lanwpc.2024.101355","url":null,"abstract":"<div><h3>Background</h3><div>Colorectal cancer (CRC) is the second most common type of cancer in China, with middle-aged and elderly adults being at high risk. However, the colonoscopy examination rate among middle-aged and elderly adults is very low. As of 2020, the colonoscopy examination rate in China was 914.8 per 100,000 people, and the distribution across regions was extremely uneven. Given the high incidence and mortality rates of colorectal cancer and the low screening rate of colonoscopies in the initial screening positive population for colorectal cancer, further interventions will be needed. The objective of this study was to use machine learning and 0.2 million consultation data to predict colorectal cancer and identify important predictors.</div></div><div><h3>Methods</h3><div>Our study was based on a population-based cross-sectional survey. We used data from 5,664 cases with colonoscopy results out of 49,701 initial positive consultations in the colorectal cancer screening project in Baoshan District, Shanghai, from 2013 to 2021. Multiple machine learning models including adaptive boosting classifier and gradient boosting machine were established to predict colorectal cancer. In the setting of outcome indicators, patients diagnosed with colorectal cancer through clinical colonoscopy results are considered to have colorectal cancer. An area under the curve (AUC) of each established model exceeding 0.7 was considered acceptable for predicting colorectal cancer. The optimal model was used to identify predictors of colorectal cancer.</div></div><div><h3>Findings</h3><div>The incidence of colorectal cancer and the colonoscopy rate is 3.58% (203/5664) and 11.4% (5664/49,701). Non-invasive predictors such as sociodemographic information, behavioural history, and medical history were used to predict the current occurrence of colorectal cancer. In our study, the accuracy of Gradient Boosting Machine, Support Vector Machine, and Light Gradient Boosting Machine reached 0.86, while the accuracy of eXtreme Gradient Boosting reached 0.84 in predicting the occurrence of colorectal cancer. Among the variables predicting colorectal cancer, age, occupation, education, history of bowel cancer in first-degree relatives, history of cholecystitis are important predictors.</div></div><div><h3>Interpretation</h3><div>Using machine learning methods and non-invasive predictors can accurately predict colorectal cancer in individuals with positive initial screening results for colorectal cancer. Our machine learning predictive models can provide further risk for colorectal cancer, which may help increase the colonoscopy examination rate among individuals with positive initial screening results. In individuals with positive colorectal cancer screenings, colonoscopy rates are low. Our machine learning models can enhance screening rates, aiding in disease prevention.</div></div><div><h3>Funding</h3><div>This study was supported by Health Promotion and Education o","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101355"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using machine learning algorithms to predict colorectal polyps

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2024.101356

Xingjian Xiao , Shiyou Liu , Kubra Maqsood , Xiaohan Yi , Guoqun Xie , Hailei Zhao , Bo Sun , Jianying Mao , Xianglong Xu

{"title":"Using machine learning algorithms to predict colorectal polyps","authors":"Xingjian Xiao , Shiyou Liu , Kubra Maqsood , Xiaohan Yi , Guoqun Xie , Hailei Zhao , Bo Sun , Jianying Mao , Xianglong Xu","doi":"10.1016/j.lanwpc.2024.101356","DOIUrl":"10.1016/j.lanwpc.2024.101356","url":null,"abstract":"<div><h3>Background</h3><div>Colorectal cancer (CRC) is the third most common cancer worldwide, and colorectal polyps (CRP) represent a necessary pathway to the development of CRC. Surveys indicate that the prevalence of colorectal polyps is 20% at age 45, increasing to over 50% to 60% by age 85 globally. In China, the prevalence of colorectal polyps among residents is approximately 18.1%, and there is a certain correlation with age: the older the age, the higher the prevalence. Until now, no studies have been conducted on utilizing non-invasive factors to predict colorectal polyps.</div></div><div><h3>Methods</h3><div>Our study was based on a population-based cross-sectional survey. We included data from 5,461 cases with colonoscopy results among 49,701 initial positive consultations in the colorectal cancer screening project conducted in Baoshan District, Shanghai, from 2013 to 2021. Multiple machine learning models including adaptive boosting classifier and gradient boosting machine were established to predict colorectal polyps. In the setting of outcome indicators, patients diagnosed with colorectal polyps through clinical colonoscopy results, pathological findings, and imaging techniques are considered to have colorectal polyps. An area under the curve (AUC) of each established model exceeding 0.7 was considered acceptable for predicting colorectal polyps. The optimal model was used to identify predictors of colorectal polyps.</div></div><div><h3>Findings</h3><div>Non-invasive predictors such as sociodemographic information, behavioural history, and medical history were used to predict the current occurrence of colorectal. In our study, the AUC of Random Forest and eXtreme Gradient Boosting reached 0.71, Adaptive Boosting Machine, Gradient Boosting Machine and Light Gradient Boosting Machine reached 0.7 in predicting the occurrence of colorectal cancer. Among the various variables predicting colorectal polyps, age, smoking, gender, cancer history, FOBT (Fecal Occult Blood Test), occupation, and education level are important predictors of colorectal polyps.</div></div><div><h3>Interpretation</h3><div>Using non-invasive factors and machine learning algorithms can accurately predict the occurrence of colorectal polyps in individuals with positive initial screening results. In the context of low colonoscopy examination rates, our machine learning predictive models may help prompt patients to undergo further examinations and interventions, thereby improve the earlier diagnosis and treatment. The rate of colonoscopy examinations is very low, even among individuals with positive initial screening results. We propose a machine learning approach that can identify individuals with colorectal polyps in this group, thereby increasing the screening rate for colorectal cancer and helping to prevent the disease.</div></div><div><h3>Funding</h3><div>This study was supported by Health Promotion and Education of the Key medical Specialty of Baoshan District, ","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101356"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improvement of early gastric cancer detection via a serum-based sequential screening strategy (4S): a prospective large-scale nationwide study in China

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2024.101286

Xianzhu Zhou, Yiqi Du

{"title":"Improvement of early gastric cancer detection via a serum-based sequential screening strategy (4S): a prospective large-scale nationwide study in China","authors":"Xianzhu Zhou, Yiqi Du","doi":"10.1016/j.lanwpc.2024.101286","DOIUrl":"10.1016/j.lanwpc.2024.101286","url":null,"abstract":"<div><h3>Background</h3><div>Gastric cancer (GC) is one of the most important cancers that warrant screening. A sequential strategy incorporating risk stratification may identify the minority for further endoscopic examination, and biomarkers of gastric atrophy could serve as effective prescreening tools at a low cost. However, its feasibility and acceptability has yet to be fully validated in real-world settings, and in which scenarios a higher early cancer detection rate can be achieved remains unclear.</div></div><div><h3>Methods</h3><div>This multicenter population-based prospective study was conducted in 266 participating institutions throughout China, spanning sites of communities, hospital (outpatient clinics), and physical exam centers, from 2022 to 2024. Adults aged 40–80 years, with or without mild symptoms, meeting the criteria for being at risk of GC, were invited for serological risk evaluation by pepsinogen and gastrin-17 risk panel. Those identified as intermediate or high risk were subsequently recommended for gastroscopy, establishing the serum-based sequential screening strategy (4S) group. Meanwhile, consecutive endoscopic diagnoses were collected in a real-world clinical setting, set as the control group. The rate of gross screening positivity, endoscopic positivity, early cancer detection, and endoscopic compliance, were compared between the two groups, and among the three screening sites within the ‘4S’ group.</div></div><div><h3>Findings</h3><div>In the ‘4S' group, 106,088 participants underwent serological risk assessments and 33.0% (34,979/106,068) fell into the medium to high-risk cohort, of which 33.3% (11,660/34,979) invitees underwent gastroscopy as recommended. Meanwhile, 27,764 subjects were included in the control group. The gross screening positive rate in the ‘4S’ group achieved 3.0‰, and gastroscopy uptake increase with risk prescreening scores (OR = 3.96, P < 0.001). When compared to the control group, the implementation of '4S' screening significantly increased the endoscopic positivity rate (2.2% vs. 0.8%, P < 0.001), and doubled the rate of early cancer detection (62.3% vs. 26.9%, P < 0.001). Compared with screening in hospital setting, community-based screening and physical examinations demonstrated superior capacity to detect tumors at an early stage (77.8% and 77.1% vs. 55.0%, P = 0.008 and 0.002), even though more cases of GC were found in the hospital setting (2.6% vs. 0.9% in community and 1.6% in physical exam). Also, the physical exam showed a poor adherence to gastroscopy (20.5% vs. 41.0% in hospital and 32.2% in community). Community or hospital-based screening showed acceptable cost-effective results by health economic analysis.</div></div><div><h3>Interpretation</h3><div>‘4S’ strategy stands out as a practical and economical option in China, as well as in countries encountering similar high-risk GC population. Community screening is highly recommended to improve early GC detection. More ","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101286"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Baseline T2-based all-in-one automated deep learning management system for neoadjuvant therapy efficacy and prognosis in locally advanced rectal cancer

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2024.101398

Kui Sun, Siyi Lu, Hao Wang, Wei Fu

{"title":"Baseline T2-based all-in-one automated deep learning management system for neoadjuvant therapy efficacy and prognosis in locally advanced rectal cancer","authors":"Kui Sun, Siyi Lu, Hao Wang, Wei Fu","doi":"10.1016/j.lanwpc.2024.101398","DOIUrl":"10.1016/j.lanwpc.2024.101398","url":null,"abstract":"<div><h3>Background</h3><div>Current methods for assessing the efficacy of neoadjuvant therapy and predicting patient survival and recurrence risk in locally advanced rectal cancer prior to treatment are limited. This study aimed to develop a multi-module automated deep learning system to evaluate the pathological complete response (pCR) and prognosis of neoadjuvant therapy in patients at baseline.</div></div><div><h3>Methods</h3><div>This multicenter study retrospectively included T2-weighted images from a total of 354 patients with pathologically confirmed locally advanced rectal cancer who received neoadjuvant therapy from 2018 to 2022. The long-term prognosis of patients was also recorded, including overall survival (OS) and disease-free survival (DFS). Center I contained 227 patients as the development cohort, and centers II and III contained 72 and 55 patients as the external test cohorts, respectively. Lesion delineation was performed manually by a radiologist with ten years of experience. Image preprocessing, including N4 bias field correction, resampling, and image normalization, was performed prior to analysis. The study consisted of four main modules; first, an advanced 3D-SwinUNETR segmentation module was constructed and trained using a development cohort. After 15000 iterations, the best model is saved and the corresponding prediction mask is generated. Second, based on the generated prediction masks, three different analysis modules are used. First, a 3D-ResNet-152 model is constructed and trained with the development cohort to predict pCR for patients. Second, based on the 3D-ResNet-152 model framework, quantitative deep features (QDLs) were extracted, and a prediction model was constructed to evaluate pCR through a feature screening method. Third, radiomics features (RFs) are extracted, and a predictive model is constructed to evaluate pCR through feature screening methods. Finally, a fusion model was constructed based on the three modules to assess neoadjuvant therapy efficacy, OS, and DFS. Dice similarity coefficients (DSC) was used to evaluate the segmentation model, Area under the receiver operating characteristic curve (AUC) was used to assess the predictive performance of neoadjuvant efficacy, Kaplan Meier was used for DFS and OS analysis, and Log-rank was used to test for statistical differences.</div></div><div><h3>Findings</h3><div>In the segmentation module, the DSC for the two external cohorts was 0.703±0.020 and 0.698±0.025, respectively. The fusion model demonstrated the best efficacy for assessing pCR, achieving AUCs of 0.756 and 0.751. Log-rank analysis indicated the fusion model's effectiveness in risk-stratifying OS, with p-values of 0.033 and 0.023, and suggested potential stratification for DFS, with p-values of 0.068 and 0.044.</div></div><div><h3>Interpretation</h3><div>This deep learning-based approach can effectively assess the neoadjuvant therapy efficacy and long-term prognosis at baseline.</div></div>","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101398"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Closing the gap in dementia research by community-based cohort studies in the Chinese population

IF 7.6 1区医学

The Lancet Regional Health: Western Pacific Pub Date : 2025-02-01 DOI: 10.1016/j.lanwpc.2025.101465

Xiaowen Zhou , Zhenxu Xiao , Wanqing Wu , Yuntao Chen , Changzheng Yuan , Yue Leng , Yao Yao , Qianhua Zhao , Albert Hofman , Eric Brunner , Ding Ding

{"title":"Closing the gap in dementia research by community-based cohort studies in the Chinese population","authors":"Xiaowen Zhou , Zhenxu Xiao , Wanqing Wu , Yuntao Chen , Changzheng Yuan , Yue Leng , Yao Yao , Qianhua Zhao , Albert Hofman , Eric Brunner , Ding Ding","doi":"10.1016/j.lanwpc.2025.101465","DOIUrl":"10.1016/j.lanwpc.2025.101465","url":null,"abstract":"<div><div>China accounts for 1/5 of the global population and China faces a particularly heavy dementia burden due to its rapidly ageing population. Unique historical events, genetic background, sociocultural factors, lifestyle, and the COVID-19 pandemic further influence cognitive outcomes in the Chinese population. We searched PubMed, Web of Science, and Embase for community-based cohort studies related to dementia in the Chinese population, and summarized the characteristics, methodologies, and major findings published over the last 25 years from 39 cohorts. We identified critical research gaps and propose future directions, including enhancing sample representativeness, investigating China-specific risk factors, expanding exposure measurements to the whole life-span, collecting objective data, conducting administer-friendly domain-specific cognitive assessments, adopting pathological diagnostic criteria, standardizing biobank construction, verifying multi-modal biomarkers, examining social and genetic-environmental aspects, and monitoring post-COVID cognitive health, to approach high quality of dementia studies that can provide solid evidence to policy making and promote global brain health research.</div></div>","PeriodicalId":22792,"journal":{"name":"The Lancet Regional Health: Western Pacific","volume":"55 ","pages":"Article 101465"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11788756/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143123676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0