Publications by authors named "Weiheng He"
Article Synopsis
- Lumbar disc herniation (LDH) is a prevalent source of lower back pain and sciatica, with posterior lumbar interbody fusion (PLIF) being a standard treatment method, prompting a study on predicting blood transfusion needs during surgery.
- This study involved 6,241 patients across 22 medical centers in China and utilized various machine learning techniques to create an optimal predictive model for intraoperative blood transfusion using robust evaluation methods.
- The best-performing model, a simulated annealing support vector machine recursive + stacking model, achieved an area under the curve of 0.884, leading to the creation of a publicly accessible web calculator to aid clinicians in decision-making and improve patient management.
Development of machine learning model for predicting prolonged operation time in lumbar stenosis undergoing posterior lumbar interbody fusion: a multicenter study.
Spine J
October 2024
Article Synopsis
- - The research focuses on developing a clinical model to predict which patients undergoing posterior lumbar interbody fusion (PLIF) for lumbar spinal stenosis are likely to experience prolonged surgical times, which can lead to complications and affect recovery.
- - A total of 3,233 patients from 22 hospitals in China from 2015 to 2022 were included in the study, and their data was analyzed using machine-learning techniques to identify key factors associated with longer surgery durations.
- - The study utilized a training cohort and four test groups, applying various algorithms and performance evaluations to create a predictive model, ultimately aiming to enhance patient safety and surgical outcomes.
Article Synopsis
- The research focused on creating a machine learning model to predict the risk of extended hospital stays before surgery, aiming to enhance patient management.
- Patients who had posterior spinal deformity surgery in China between 2015 and 2022 were included, and their preoperative data was analyzed using various machine learning techniques to identify risk factors.
- The K Nearest Neighbors algorithm was the most effective in predicting prolonged hospitalization, with key factors including preoperative hemoglobin, height, BMI, age, and white blood cells, leading to the development of a web-based calculator for practical use.
Facing extreme pressure from an increasing population and climate degeneration, it is important to explore a green, safe and environmentally sustainable food source, especially for protein-enriched diets. Plant proteins have gained much attention in recent years, ascribing to their high nutritional value and environmental friendliness. In this review, we summarized recent advances in walnut protein with respect to its geographical distribution, structural and physiochemical properties and functional attributes.
View Article and Find Full Text PDFObjectives: There is limited in-depth research exploring persistent symptoms and conditions among children and adolescents who contracted COVID-19 illness that required hospitalisation. The main objective of this study was to conduct qualitative interviews among families who had a child hospitalised with COVID-19 illness to elucidate their child's physical, mental and social health outcomes months after initial acute infection.
Design, Setting And Participants: A qualitative study that composed of in-depth interviews among families with a child hospitalised with COVID-19 illness in one large urban US paediatric healthcare system.
A cationic perylene probe was designed and synthesized for sensitive determination of tartrazine. In the presence of tartrazine, the fluorescence of the perylene probe was quenched by efficient supramolecular self-assembly of the perylene derivate. The quenching is caused by the synergistic effect of noncovalent interactions including static electricity, π-π stacking, and hydrophobic interaction.
View Article and Find Full Text PDFComparison of Long-Term Complications of COVID-19 Illness among a Diverse Sample of Children by MIS-C Status.
Int J Environ Res Public Health
October 2022
Most pediatric COVID-19 cases are asymptomatic; however, a small number of children are diagnosed with multisystem inflammatory syndrome in children (MIS-C), a rare but severe condition that is associated with SARS-CoV-2 infection. Persistent symptoms of COVID-19 illness in children diagnosed with/without MIS-C is largely unknown. A retrospective EHR review of patients with COVID-19 illness from one pediatric healthcare system to assess the presence of acute (<30 days) and chronic (≥30, 60-120, and >120 days) long-term COVID symptoms was conducted.
View Article and Find Full Text PDF