Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Local Anesthetics: Pharmacokinetics01:13

Local Anesthetics: Pharmacokinetics

850
The potency and duration of action of local anesthetics (LAs) are determined by their pharmacokinetics. Pharmacokinetics describes how LAs are absorbed, distributed, metabolized, and eliminated from the body. When administered to the vascular tissues, LAs are quickly absorbed and enter the systemic circulation, reducing their localized effects. Adding vasoconstrictors such as epinephrine to LAs reduces their absorption into the systemic circulation, making them clinically effective. The...
850
Local Anesthetics: Chemistry and Structure-Activity Relationship01:27

Local Anesthetics: Chemistry and Structure-Activity Relationship

5.4K
Local anesthetics (LAs) are drugs that induce a temporary loss of sensation in a limited body area, preventing pain. Cocaine was the first local anesthetic discovered in the late 19th century. Cocaine is a benzoic acid ester obtained from the leaves of coca shrubs and was often used for its psychotropic effects. Cocaine was first isolated in 1860 by Albert Niemann. Sigmund Freud studied the physiological actions of cocaine. Carl Koller later introduced it into clinical practice in 1884 as a...
5.4K
Drug Nomenclature01:17

Drug Nomenclature

2.3K
During the development of a new pharmaceutical, the manufacturer initially assigns a code name to the drug. Once approved, the drug receives a United States Adopted Name (USAN)—a generic, nonproprietary designation. Upon being listed in the United States Pharmacopeia, this nonproprietary name becomes the drug's official name. Additionally, the manufacturer assigns a proprietary name or trademark, which serves as the brand name under which the drug is marketed. It is worth noting that...
2.3K
Local Anesthetics: Mechanism of Action01:23

Local Anesthetics: Mechanism of Action

2.5K
Local anesthetics (LAs) block sensory and motor impulses by inhibiting the sodium channels on the nerve cell membranes. This induces temporary loss of sensation, relieving pain in a specific body area.
Local anesthetics are amphiphilic molecules consisting of a hydrophobic aromatic part linked to a hydrophilic group by an ester or amide linkage. They are weak bases and are usually available as salts, which increases their solubility and stability. Once administered, LAs exist in the body either...
2.5K
Pharmacokinetic Models: Overview01:20

Pharmacokinetic Models: Overview

1.1K
Pharmacokinetic models utilize mathematical analysis to achieve a detailed quantitative understanding of a drug's life cycle within the body. They are instrumental in simulating a drug's pharmacokinetic parameters, predicting drug concentrations over time, optimizing dosage regimens, linking concentrations with pharmacologic activity, and estimating potential toxicity.
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
1.1K
Local Anesthetics: Common Agents and Their Applications01:23

Local Anesthetics: Common Agents and Their Applications

548
Local anesthetics (LAs) are commonly used for various applications in medical and dental procedures. Some of the common agents used are cocaine, lidocaine, and bupivacaine.
Cocaine is an ester of benzoic acid and methylecgogine. It is used to anesthetize and vasoconstrict locally. Currently, it is used primarily for topical applications. It is beneficial for surgeries on the upper respiratory tract, providing anesthesia and shrinking the mucosa. Cocaine in the form of cocaine hydrochloride is...
548

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

QutRNA2: robust tRNA modification discovery from Nanopore direct tRNA sequencing.

NAR genomics and bioinformatics·2026
Same author

Circtools 2.0: a comprehensive framework for enhanced circular RNA bioinformatics.

BMC bioinformatics·2026
Same author

The SURROGATOR Framework for Context-Aware Surrogation of Privacy Sensitive Information in Medical Text.

Studies in health technology and informatics·2026
Same author

RBM20 isoform regulation by independent transcription start sites adapts alternative splicing in development and disease.

Nature communications·2026
Same author

CAMK2D causes heart failure in mice with RBM20 cardiomyopathy.

Nature cardiovascular research·2026
Same author

Enhancing KLF15 activity in cardiomyocytes: a novel approach to prevent pathological reprogramming and fibrosis via nuclease-deficient dCas9VPR.

Signal transduction and targeted therapy·2026

Video Experimental Relacionado

Updated: Sep 10, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

681

Extracción de información sobre medicamentos mediante el uso de modelos locales de lenguaje grande

Phillip Richter-Pechanski1, Marvin Seiferling2, Christina Kiriakou3

  • 1Section of Bioinformatics and Systems Cardiology, Klaus Tschira Institute for Integrative Computational Cardiology, Im Neuenheimer Feld 669, 69120 Heidelberg, DE, Germany; Department of Internal Medicine III, University Hospital, Im Neuenheimer Feld 410, 69120 Heidelberg, DE, Germany; German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim, Im Neuenheimer Feld 669, 69120 Heidelberg, DE, Germany; Informatics for Life, Im Neuenheimer Feld 669, 69120 Heidelberg, DE, Germany; Department of Computational Linguistics, Heidelberg University, Im Neuenheimer Feld 325, 69120 Heidelberg, DE, Germany.

Journal of biomedical informatics
|August 23, 2025
PubMed
Resumen

Los modelos locales de lenguaje grande (LLM) ajustados logran la extracción de medicamentos de última generación del texto clínico, mejorando la precisión y la transparencia. Estos modelos ofrecen soluciones eficientes y confiables para entornos de atención médica del mundo real.

Palabras clave:
La PNL clínicaEl ajuste finoInterpretabilidadGrandes modelos de lenguajeLas llamasExtracción de información sobre el medicamento

Más Videos Relacionados

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

575
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

634

Videos de Experimentos Relacionados

Last Updated: Sep 10, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

681
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

575
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

634

Área de la Ciencia:

  • La informática médica
  • Procesamiento del lenguaje natural
  • Inteligencia artificial

Sus antecedentes:

  • La extracción de información sobre medicamentos de un texto clínico no estructurado es vital, pero es un desafío debido al esfuerzo manual y los errores.
  • Los métodos de automatización actuales se enfrentan a limitaciones como las demandas de experiencia, los límites de tiempo, la infraestructura de TI y las necesidades de transparencia.
  • Los modelos generativos de lenguaje grande (LLM) y el ajuste fino eficiente de parámetros ofrecen soluciones prometedoras.

Objetivo del estudio:

  • Evaluar los LLM locales para la extracción automática de información de medicación de extremo a extremo.
  • Evaluar el rendimiento de los LLM afinados en conjuntos de datos clínicos tanto en inglés como en alemán.
  • Mejorar la transparencia de las predicciones mediante técnicas de explicabilidad.

Principales métodos:

  • Utilizó el reconocimiento de entidades con nombre y la extracción de relaciones con LLM locales.
  • Se emplean instrucciones de restricción de formato y una línea de retroalimentación automatizada para la evaluación.
  • Valores Shapley aplicados a nivel de token para visualizar y cuantificar las contribuciones de token.

Principales resultados:

  • Los modelos Llama ajustados obtuvieron nuevos resultados de vanguardia en datos de inglés, mejorando las puntuaciones de F1 hasta en 10 pp. para los efectos adversos del medicamento y 6 pp. por razones de medicación.
  • Llama estableció un nuevo punto de referencia en el conjunto de datos alemán, superando los métodos tradicionales hasta en 16 pp. el puntaje micro promedio F1.
  • OpenBioLLM mostró limitaciones en las salidas estructuradas y alucinaciones experimentadas.

Conclusiones:

  • Los LLM generativos locales de código abierto ajustados superan los métodos actuales de última generación para la extracción de información sobre medicamentos.
  • Estos modelos proporcionan un alto rendimiento con recursos limitados en entornos clínicos, eficaces tanto en inglés como en alemán.
  • Los valores de Shapley mejoran la transparencia de la predicción, ayudando a la toma de decisiones clínicas.