A5044290630- Radiomics and Machine Learning in Medical Imaging
- Breast Cancer Treatment Studies
- Glioma Diagnosis and Treatment
- AI in cancer detection
- Arctic and Antarctic ice dynamics
- Head and Neck Cancer Studies
- Climate change and permafrost
- Advanced Chemical Sensor Technologies
- MRI in cancer diagnosis
- Olfactory and Sensory Function Studies
- Hydrology and Watershed Management Studies
- Long-Term Effects of COVID-19
- Plant Virus Research Studies
- Statistical Methods in Clinical Trials
- Bone fractures and treatments
- Cerebrovascular and Carotid Artery Diseases
- Artificial Intelligence in Healthcare and Education
- Global Cancer Incidence and Screening
- Smart Agriculture and AI
- Acute Ischemic Stroke Management
- Water Resources and Management
- Mental Health Research Topics
- Prostate Cancer Diagnosis and Treatment
- Remote Sensing and Land Use
- Hip and Femur Fractures
Tongji University
2022-2025
Chinese Academy of Sciences
2024-2025
Xinjiang Institute of Ecology and Geography
2024-2025
University of Chinese Academy of Sciences
2024-2025
Huazhong Agricultural University
2022
Stroke is an acute disorder and dysfunction of the focal neurological system that has long been recognized as one leading causes death severe disability in most regions globally. This study aimed to supplement exploit multiple comorbidities, laboratory tests demographic factors more accurately predict related stroke, furthermore, make inferences about heterogeneity treatment stroke patients guide better planning.We extracted data from Medical Information Mart Intensive Care (MIMIC)-IV...
Abstract Background There are potential uncertainties and overtreatment existing in radical prostatectomy (RP) for prostate cancer (PCa) patients, thus identifying optimal candidates is quite important. Purpose This study aims to establish a novel causal inference deep learning (DL) model discern whether patient can benefit more from RP identify heterogeneity treatment responses among PCa patients. Methods We introduce the Self-Normalizing Balanced individual effect survival data (SNB). Six...
Abstract Background Due to the heterogeneity of low‐grade gliomas (LGGs), lack randomized control trials, and strong clinical evidence, effect extent resection (EOR) is currently controversial. Aim To determine best choice between subtotal (STR) gross‐total (GTR) for individual patients identify features that are potentially relevant treatment heterogeneity. Methods Patients were enrolled from SEER database. We used a novel DL approach make recommendations with LGG. also made causal...
ObjectivesTo characterize the prevalence, severity, correlation with initial symptoms, and role of vaccination in patients COVID-19 smell or taste alterations (STAs).MethodsWe conducted an observational study infected SARS-CoV-2 Omicron admitted to three hospitals between May 17 June 16, 2022. The olfactory gustatory functions were evaluated using survey numerical visual analog scale at two time points.ResultsThe T1 T2 point assessments completed by 688 385 participants, respectively....
Abstract Background The role of surgery in metastatic breast cancer (MBC) is currently controversial. Several novel statistical and deep learning (DL) methods promise to infer the suitability at individual level. Objective objective this study was identify most applicable DL model for determining patients with MBC who could benefit from type required. Methods We introduced survival regression mixture effects (DSME), a semi‐parametric integrating three causal inference methods. Six models...
There is a lack of individualized evidence on surgical choices for glioblastoma (GBM) patients.
High- and very high-resolution (HR, VHR) remote sensing (RS) images can provide comprehensive intricate spatial information for land cover classification, which is particularly crucial when analyzing complex built-up environments. However, the application of HR VHR to large-scale detailed mapping always constrained by intricacy classification models, exorbitant cost collecting training samples, geographical changes or acquisition conditions. To overcome this limitation, we propose an...
The conventional treatment for locally advanced head and neck squamous cell carcinoma (LA-HNSCC) is surgery; however, the efficacy of definitive chemoradiotherapy (CRT) remains controversial. This study aimed to evaluate ability deep learning (DL) models identify patients with LA-HNSCC who can achieve organ preservation through CRT provide individualized adjuvant recommendations are better suited surgery. Five were developed recommendations. Their performance was assessed by comparing...
Invasive plants (IPs) pose a significant threat to local ecosystems. Recent advances in remote sensing (RS) and deep learning (DL) significantly improved the accuracy of IP detection. However, mainstream DL methods often require large, high-quality labeled data, leading resource inefficiencies. In this study, framework called adversarial positive-unlabeled (APUL) was proposed achieve high-precision detection using limited number target plant samples. APUL employs dual-branch discriminator...
This study aimed to evaluate the impact of nipple-sparing mastectomy (NSM) and modified radical (MRM) on individual survival outcomes assess potential neoadjuvant systemic therapy (NST) in reducing surgical intervention requirements. To develop treatment recommendations for breast cancer patients, five machine learning models were trained. mitigate bias allocation, advanced statistical methods, including propensity score matching (PSM) inverse probability weighting (IPTW), applied. NSM...
There is a lack of studies exploring the performance Transformers-based language models in common risks assessment among psychiatric inpatients. We aim to develop scalable risk model using multidimensional textualized data and test stability, robustness, benefit this approach. In real-world cohort study, deep learning was developed validated first hospitalized cases diagnosed with schizophrenia, bipolar disorder, depressive disorder between January 2016 March 2023 three hospitals. The...
Background This study focused on minimizing the costs and toxic effects associated with unnecessary chemotherapy. We sought to optimize adjuvant therapy strategy, choosing between radiotherapy (RT) chemoradiotherapy (CRT), for patients based their specific characteristics. selection process utilized an innovative deep learning method. Methods trained six machine (ML) models advise most suitable treatment glioblastoma (GBM) patients. To assess protective efficacy of these ML models, we...
At present, the existing vegetable grafting machines are cutting and operations for a single plant or row. They need to manually automatically grab seedlings, their efficiency is not significantly higher than that of manual techniques. In this paper, grafted melon seedlings were subject research. Based on splice-grafting method, we designed clamping positioning device full-tray mechanical realize by locating completing process without damaging seedlings. The results show success rate pumpkin...
Acute kidney injury (AKI) is a common complication associated with significant morbidity and mortality in high-energy trauma patients. Given the poor efficacy of interventions after AKI development, it important to predict before its diagnosis. Therefore, this study aimed develop models using machine learning algorithms risk patients femoral neck fractures. We developed machine-learning Medical Information Mart from Intensive Care (MIMIC)-IV database. was predicted 10 predictive three-time...
Abstract Purpose The use of postoperative radiotherapy (PORT) in patients with oral squamous cell carcinoma (OCSCC) lacks clear boundaries due to the non‐negligible toxicity accompanying its remarkable cancer‐killing effect. This study aims at validating ability deep learning models develop individualized PORT recommendations for OCSCC and quantifying impact patient characteristics on treatment selection. Methods Participants were categorized into two groups based alignment between...
Considering the huge population in China, available mental health resources are inadequate. Thus, our study aimed to evaluate whether questionnaires, serving as auxiliary diagnostic tools, have efficient ability outpatient psychiatric services.We conducted a retrospective of Chinese outpatients. Altogether 1,182, 5,069, and 4,958 records Symptom Checklist-90 (SCL-90), Hamilton Anxiety Rating Scale (HAM-A), Depression (HAM-D), respectively, were collected from March 2021 July 2022. The...
Climate change and human activities have significantly altered the spatial temporal distribution of surface water in Irtysh River basin (IRB), while inter-annual trend with high resolution can be detected by using Landsat imagery, it is difficult to analyze seasonal variation characteristics long time series scenario. In this work, monthly cloud-filled area (SWA) IRB from 1985 2022 were reconstructed at 30 accuracy (> 94%) Landsat4/5/7/8/9 satellite imageries random forest (RF) historical...
There is ongoing uncertainty about the effectiveness of various adjuvant treatments for low-grade gliomas (LGGs). Machine learning (ML) models that predict individual treatment effects (ITE) and provide recommendations could help tailor to each patient's needs.
To assess deep learning models for personalized chemotherapy selection and quantify the impact of baseline characteristics on treatment efficacy elderly head neck squamous cell carcinoma (HNSCC) patients who are not surgery candidates. A comparison was made between whose treatments aligned with model recommendations those did not, using overall survival as primary metric. Bias addressed through inverse probability weighting (IPTW), patient choice analyzed via mixed-effects regression. Four...
Background: Anosmia and dysgeusia are key symptoms of SARS-CoV-2 infection. We aimed to characterize the prevalence, severity, timing, associated symptoms, impact vaccination in COVID-19 patients exhibiting these symptoms.Methods: conducted an observational study with mild Omicron variant infections admitted three mobile hospitals between April 20 May 16, 2022. Olfactory gustatory function were evaluated using Taste Smell Survey (TSS) numerical visual analog scale (VAS). Primary outcomes...