Результаты поиска

Validation of the Medicare-Enhanced Laboratory and Demographics (MELD™) Dataset: A Comprehensive Psychometric, Epidemiologic, and Predictive-Utility Assessment of a 60-Million-Patient Real-World Evidence Resource.

BackgroundReal-world evidence studies increasingly rely on integrated data resources that combine Medicare fee-for-service claims with electronic medical records (EMRs), laboratory results, and patient-reported outcomes. The Medicare-Enhanced Laboratory and Demographics (MELD™) dataset, developed by Columbia Data Analytics, spans 2020 through 2024 and contains 60 million unique patients, roughly 1 billion visits, and more than 241 000 clinicians. Its data-quality properties must be characterized before regulatory-grade use.ObjectiveTo provide a preregistered, multidomain validation of MELD, qu

The Reporting, Use, and Validity of Patient-Reported Outcomes in Multiple Myeloma in Clinical Trials: A Systematic Literature Review.

BACKGROUND: Patient-reported outcomes (PROs) are becoming increasingly important in supporting clinical outcomes in clinical trials. In multiple myeloma (MM), PRO measurement is useful to reveal how treatment affects physical, psychosocial, and functional behaviour as well as symptoms and treatment-related adverse events to evaluate the benefit-risk ratio of a particular drug or drug combination. We report the types of PRO instruments used in MM, the frequency in which they are utilised in randomised controlled trials (RCTs), and the consistency of their reporting. METHODS: The European Hemat

Mechanistic study of pre-eclampsia and macrophage-associated molecular networks: bioinformatics insights from multiple datasets.

BACKGROUND: Pre-eclampsia is a pregnancy-related disorder characterized by hypertension and proteinuria, severely affecting the health and quality of life of patients. However, the molecular mechanism of macrophages in pre-eclampsia is not well understood. METHODS: In this study, the key biomarkers during the development of pre-eclampsia were identified using bioinformatics analysis. The GSE75010 and GSE74341 datasets from the GEO database were obtained and merged for differential analysis. A weighted gene co-expression network analysis (WGCNA) was constructed based on macrophage content, and

Совпадение в полном тексте источника
… Random forest is an ensemble learning algorithm based on decision trees. It uses sampling and replacement methods to select multiple samples from the sample set as the training set, and generates a decision tree using the sampled sample set. …

Пример MobileNetV2-Based Искусственный интеллект для быстрого и точного диагностирования множественных склерозов

Множественный склероз (MS) — хроническое аутоиммунное заболевание центральной нервной системы, которое сильно влияет на молодых людей из-за его изнурительной природы. Патогенез болезни сосредоточен на воспалении и процессах нейродегенерации. Воспаление ассоциируется с рецидивами, в то время как нейродегенерация возникает на прогрессивных стадиях болезни. Для диагностики MS обычно используется магнитно-резонансная съемка (MRI), и имеются такие руководящие принципы, как критерии McDonald. МРТ является важным инструментом для демонстрации пространственного распределения и изменений во времени в э

Идентификация и каталог регуляторов вирусной транскрипции заболеваний человека.

Вирусные геномы кодируют регуляторы вирусной транскрипции (vTRs), которые манипулируют экспрессией гена хоста, чтобы облегчить воспроизведение и избежать иммунной обнаружения. Тем не менее их роль в нераковых болезнях по-прежнему в значительной степени недооценивается. Здесь мы представили 268 новых кандидатов в VTR из 14 из 20 вирусных семей, которые мы расследовали. Мы картировали связующие профили генома VTR и определили их потенциальные цели человека, которые были обогащены иммунно-посредованными путями, нейродегенеративными расстройствами и раком. На основе анализа предпочтений VTR, имеющ

Prospective external validation of a three-predictor frailty model for 90-day survival and complications following spinal metastasis surgery.

Background contextSurgical decision-making in patients with spinal metastases remains complex due to the need to balance potential surgical benefits with limited survival and common frailty. Predictive models can assist in this process, but their clinical utility is often limited by complexity and lack of validation.PurposeTo externally validate a simple three-predictor frailty model for 90-day survival and complications, and to compare its performance with other commonly used tools.Study design/settingProspective external validation study conducted at a single tertiary cancer center.Patient s

Прогнозирование релапирования и индивидуализированная модель лечения-воздействия при повторном склерозе: систематический обзор.

ВВЕДЕНИЕ: Индивидуальное прогнозирование результатов, связанных с рецидивом, может способствовать отбору и мониторингу лечения при повторном склерозе. Однако существующие исследования существенно отличаются друг от друга по клиническим целям, целевым результатам, подходам к моделированию и стратегиям проверки. МЕТОДЫ: Мы провели систематический обзор в соответствии с ПРИСМА 2020. Пубмед, Web of Science, IEEE Xplore и Scopus были найдены записи на английском языке, опубликованные на английском языке. 1 Январь 2010 в адрес 14 Январь 2026. Были включены исследования по разработке или оценке модел

Efficacy and safety of de-escalation bone- modifying agents for cancer patients with bone metastases: a systematic review and meta-analysis.

BackgroundCompared with application of bone-modifying agents (BMAs) every 4 weeks, it is unclear whether 12-weekly de-escalated therapy can be used as a substitute strategy.MethodsA systematic search of PubMed, EMBASE, and the Cochrane Register of Controlled Trials until November 22, 2017, was performed. Randomized controlled trials (RCTs) were included to assess skeletal-related event (SRE) rates, adverse events, and bone turnover biomarkers, comparing 12-weekly de-escalated treatments with standard 4-weekly dosage regimens. Risk ratios (RRs) with 95% CIs were pooled in fixed-effect meta-anal

Unlocking artificial intelligence, machine learning and deep learning to combat therapeutic resistance in metastatic castration-resistant prostate cancer: a comprehensive review.

Metastatic castration-resistant prostate cancer (mCRPC) remains a formidable clinical challenge despite advancements in therapy. This narrative review explores the role of artificial intelligence (AI), machine learning and deep learning in addressing therapeutic resistance in mCRPC. AI-driven approaches leverage integrated datasets encompassing genomics, proteomics and clinical parameters to uncover molecular mechanisms, predict treatment responses and identify biomarkers of resistance. These methodologies promise personalised treatment strategies tailored to individual patient profiles. Howev

Совпадение в полном тексте источника
… Decision trees are a specific ML technique that has demonstrated broad applicability across various cancer types, significantly improving diagnostic accuracy [ 18 – 20 ]. These applications encompass various cancer types, including breast, gastric, thyroid, prostate and colorectal cancer. …

Machine learning-based prediction of one-year mortality after alloHCT identifies the impact of pre-transplant immunity and inflammation.

Accurate prediction of mortality after allogeneic hematopoietic stem cell transplantation (alloHCT) is essential for individualized treatment decisions, yet existing clinical risk scores capture only a limited number of variables and show modest predictive performance. In our single-center retrospective analysis, we included data from 909 adult patients with hematologic malignancies undergoing alloHCT. We used 31 features to build machine-learning models to predict death within the first year after alloHCT. These features included established clinical risk factors together with pre-transplant

Множественная стратификация риска склероза и прогнозирование расходов на здравоохранение с использованием машинного обучения.

СПРАВОЧНАЯ ИНФОРМАЦИЯ: Растущая доступность медицинских данных дает возможность более активно бороться с такими хроническими заболеваниями, как множественный склероз (МС). Мы поставили перед собой цель разработать подход к машинному обучению (ML) для выявления пациентов с повышенным уровнем риска и прогнозирования их расходов на медицинское обслуживание. МЕТОДЫ: Мы провели ретроспективный анализ деидентифицированных коммерческих страховых требований 267,000 (неполные лица)631 с MS), с января 2016 по июнь 2018. Ежемесячные данные о претензиях были агрегированы, и 72 ML регрессия и 63 :: были по

Совпадение в полном тексте источника
… These approaches included K-Nearest Neighbors, decision trees, gradient boosting machines, ElasticNet generalized linear models, random forests, support vector machines, and neural networks. …

System analysis based on the T cell exhaustion‑related genes identifies CD38 as a novel therapy target for ovarian cancer.

Ovarian cancer (OV) is highly heterogeneous tumor with a very poor prognosis. Studies increasingly show that T cell exhaustion is prognostically relevant in OV. The aim of this study was to dissect the heterogeneity of T cell subclusters in OV through single cell transcriptomic analysis. The single RNA-sequencing (scRNA-seq) data of five OV patients were analyzed, and six major cell clusters were identified after threshold screening. Further clustering of T cell-associated clusters revealed four subtypes. Pathways related to oxidative phosphorylation, G2M checkpoint, JAK-STAT and MAPK signalin

Совпадение в полном тексте источника
… The x-axis represents the number of decision trees, and the y-axis represents the error rate. Random forest classifier results based on Gini coefficient. The x-axis represents genetic variables and the y-axis represents importance indices. …

Revolutionizing hematological disorder diagnosis: unraveling the role of artificial intelligence.

The integration of artificial intelligence (AI) into medical diagnostics is transforming the landscape of healthcare, particularly in hematology. AI technologies, leveraging advanced machine learning algorithms and big data analytics, are revolutionizing the diagnosis of hematological disorders such as anemia, leukemia, and lymphoma. This review explores how AI enhances diagnostic accuracy, efficiency, and patient outcomes by processing complex datasets and identifying patterns beyond human capability. AI-driven advancements in hematology include innovations in image analysis, genomic data int

Совпадение в полном тексте источника
… AI utilizes supervised learning algorithms, such as support vector machines (SVMs) and decision trees, to detect patterns in labeled hematological data [ 23 ] . These algorithms are trained on historical data to recognize specific disease characteristics and classify new patient samples. … These models incorporate decision trees, flowcharts, and rule-based systems to help clinicians evaluate options and make informed decisions. …

Искусственные интеллектуальные технологии зондирования для борьбы с раком, диабетом и COVID-19.

Интеграция искусственного интеллекта (АИ) с износимыми сенсорными технологиями может привести к революции в мониторинге и лечении различных хронических заболеваний и острых заболеваний. Комбинированные износы АИ классифицируются по таким основополагающим методам зондирования, как электрохимическая, колориметрическая, химическая, оптическая, а также давление/стабильность. Алгоритмы АИ повышают эффективность изношенных датчиков, обеспечивая индивидуализированный, постоянный надзор и прогнозный анализ, помогая распознавать время и оптимизируя терапевтические методы. В этой рукописи рассматриваютс

Совпадение в полном тексте источника
… Five ML techniques are investigated for glucose prediction: regression analysis, k-nearest neighbors, decision trees, and neural networks [ 124 ]. … ML algorithms were trained on FEM simulations with varying geometric parameters, and the best predictions were obtained with decision tree regression (DTR). Machine learning techniques can optimize MN designs for targeted drug delivery and point-of-care diagnostics in wearable devices. …

Clinical Trials of Liposomes in Children's Anticancer Therapy: A Comprehensive Analysis of Trials Registered on ClinicalTrials.gov.

ObjectiveClinical trials have become essential for driving the development of medicine. However, little is known about the current status of clinical trials on liposomes in children's anticancer therapy (LCAT). This study aimed to synthesize current finding from clinical trials of LCAT in ClinicalTrials.gov.MethodsA cross-sectional descriptive study of clinical trials on LCAT was conducted, using studies registered on ClinicalTrials.gov through December 30, 2021.ResultsA total of 74 eligible trials were identified, accounting for 4.8% (74/1552) of all trials on liposomes for cancer therapy. Am

Diagnostic and therapeutic approaches to multiple myeloma patients: 'Real-world' data from representative multicentre treatment surveys in Germany between 2008 and 2011.

A survey was conducted to investigate the standard of care for multiple myeloma in Germany, in order to clarify the status of implementation of international and national treatment guidelines. In addition, the changes in disease management over time were investigated by comparison with surveys conducted in 2008 and 2009. The survey captured a representative sample of 478 myeloma patients with a mean age of 67.9 years across various stages of the disease. Diagnostic approaches, prognostic aspects and treatment decisions were evaluated based on a survey conducted in 2011 in 58 representative cen

Development of Anticancer Peptides Using Artificial Intelligence and Combinational Therapy for Cancer Therapeutics.

Cancer is a group of diseases causing abnormal cell growth, altering the genome, and invading or spreading to other parts of the body. Among therapeutic peptide drugs, anticancer peptides (ACPs) have been considered to target and kill cancer cells because cancer cells have unique characteristics such as a high negative charge and abundance of microvilli in the cell membrane when compared to a normal cell. ACPs have several advantages, such as high specificity, cost-effectiveness, low immunogenicity, minimal toxicity, and high tolerance under normal physiological conditions. However, the develo

Evaluation of epidemiological and pathological features of symptomatic spinal metastases in Romania - what could we learn from a retrospective study?

Metastases are the most common tumors of the spine. As an important increase in the annual incidence of spinal metastases (SMs) has been observed in the last decade, the aim of this study was to describe the epidemiology and histopathological types of SMs surgically treated in the Neurosurgery Clinics of a Regional Hospital in North-Eastern Romania over a period of five years, in order to define a certain tumor profile that would benefit from an early screening. We retrospectively evaluated 115 adult patients, searching for demographic data (gender and age of the patients), primary tumor chara

Машинное обучение - Deriveed Immune Gene Signing Previsions Прогнозы прогноза и терапическая вульгарность в Множестве миеломы.

Иммунная микроокружающая среда вносит существенный вклад в биологическую и клиническую неоднородность множественной миэломы (ММ), однако молекулярные биомаркеры, связанные с иммунной деятельностью, с воспроизводимым прогнозируемым значением по-прежнему ограничены. Здесь мы разработали 12-генную генную сигнатуру, связанную с иммунным иммунитетом (ИРГС), используя интеграционную систему машинного обучения, и оценили ее прогнозируемую эффективность в различных группах MM. ИРГС последовательно стратифицировала общее выживание и оставалась независимой с точки зрения результатов после корректировки

Analysis of factors influencing the increase of extracellular water ratio in tumor patients without edema signs.

ObjectiveThis study aims to examine the factors contributing to the increase in extracellular water to total body water ratio (ECW/TBW) among tumor patients without visible edema, and to offer insights into the diagnosis and prompt management of early water retention in such patients.MethodsA cohort of 274 tumor patients admitted to Anqing First People's Hospital, affiliated with Anhui Medical University between December 2020 and December 2022, were selected, excluding those with clinically observable edema. General clinical data, main laboratory test outcomes, and body composition indices wer