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

Reliability and Validity01:29

Reliability and Validity

14.1K
Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.
14.1K
Glassware Calibration01:11

Glassware Calibration

1.5K
Accurate calibration of glassware, such as volumetric flasks, pipettes, and burettes, is essential to ensure accurate measurements in the analytical laboratory. Calibration helps maintain consistency across measurements and prevents errors arising from inaccurate volumes.
Volumetric flasks: Volumetric flasks are designed to prepare aqueous solutions of precise volumes accurately with a calibration line on the neck. To calibrate a volumetric flask, it is important to fill it with distilled...
1.5K
Instrument Calibration01:12

Instrument Calibration

779
Instrument calibration is essential for ensuring that instruments produce accurate and consistent results. It is vital in manufacturing, healthcare, testing laboratories, and scientific research. Calibration processes are specific to each instrument and help enhance data accuracy. Each instrument has a unique calibration process tailored to its design and function to improve data accuracy.
Analytical Balance Calibration
An analytical balance measures mass and requires regular calibration to...
779
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

46.1K
VSEPR Theory for Determination of Electron Pair Geometries
46.1K
Inhaled Medications01:23

Inhaled Medications

814
Inhaled medications are crucial for managing chronic obstructive pulmonary disease (COPD) and asthma. They are essential for effective treatment and control, ensuring optimal respiratory health and well-being. Inhaled medication delivers drugs directly to the lungs, providing a rapid onset of action and reducing systemic side effects compared to oral or injectable medications. Three primary types of inhalation devices are used to administer these medications: nebulizers, metered-dose inhalers...
814
Calibration Curves: Correlation Coefficient01:10

Calibration Curves: Correlation Coefficient

5.0K
In a linear calibration curve, there is a value called the calibration coefficient, denoted by 'r,' which measures the strength and the direction of association between two variables. The correlation coefficient value ranges from −1 to +1. A value of +1 indicates a perfect positive linear correlation, −1 denotes a perfect negative correlation, and 0 implies no correlation between the two variables. A positive correlation value establishes that as one variable increases, the...
5.0K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Towards transparent and reliable AI in gastroenterology: pragmatic recommendations for evaluation and reporting.

Digestive and liver disease : official journal of the Italian Society of Gastroenterology and the Italian Association for the Study of the Liver·2026
Same author

Why almost all ML models for medicine are wrong-and what we need for evidence-based medical AI.

International journal of medical informatics·2026
Same author

From Asimov's laws to Kasparov's laws: artificial intelligence, clinical work, and the design of hybrid intelligence.

Recenti progressi in medicina·2026
Same author

How AI Agreement Shapes Confidence: Evidence Across Clinical Skill Levels.

Studies in health technology and informatics·2026
Same author

Artificial intelligence-based image recognition in bronchoscopy: software development and randomized controlled trial for training evaluation in intensive care residents.

BMC medical education·2026
Same author

From algorithms to care: ten principles for responsible deployment of artificial intelligence in healthcare.

European journal of internal medicine·2026

Video Experimental Relacionado

Updated: Feb 10, 2026

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

8.0K

Métricas informadas por calibración para la fiabilidad predictiva a nivel de instancia en IA médica

Federico Cabitza1

  • 1Department of Informatics, Systems and Communication, University of Milano-Bicocca, Viale Sarca 336, Milano, 20126, Italy; Digital Health & Wellbeing Center, Fondazione Bruno Kessler (FBK), Via Sommarive, 18, Povo, Trento, 38123, Italy.

Artificial intelligence in medicine
|February 8, 2026
PubMed
Resumen

Nuevas métricas, Valor Predictivo Local (LPV) y Valor Predictivo Creíble (CPV), evalúan la fiabilidad de predicciones individuales de IA en la atención médica. Estas métricas mejoran la confianza en los sistemas de apoyo a la decisión clínica al proporcionar estimaciones de fiabilidad interpretables.

Palabras clave:
CalibraciónIntervalo de confianzaIntervalos creíblesML médicoIA transparente

Más Videos Relacionados

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.8K
A Cost-effective and Reliable Method to Predict Mechanical Stress in Single-use and Standard Pumps
07:34

A Cost-effective and Reliable Method to Predict Mechanical Stress in Single-use and Standard Pumps

Published on: August 5, 2015

9.8K

Videos de Experimentos Relacionados

Last Updated: Feb 10, 2026

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

8.0K
A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.8K
A Cost-effective and Reliable Method to Predict Mechanical Stress in Single-use and Standard Pumps
07:34

A Cost-effective and Reliable Method to Predict Mechanical Stress in Single-use and Standard Pumps

Published on: August 5, 2015

9.8K

Área de la Ciencia:

  • Inteligencia artificial en medicina
  • Sistemas de apoyo a la decisión clínica
  • Fiabilidad de la IA médica

Sus antecedentes:

  • Las métricas de rendimiento tradicionales (p. ej., precisión, sensibilidad) en los sistemas de apoyo a la decisión clínica (CDSS) no transmiten adecuadamente la fiabilidad de las predicciones individuales.
  • Los médicos requieren predicciones individuales confiables, especialmente en entornos médicos de alto riesgo.

Objetivo del estudio:

  • Introducir un marco novedoso informado por calibración con dos nuevas métricas: Valor Predictivo Local (LPV) y Valor Predictivo Creíble (CPV).
  • Proporcionar estimaciones de fiabilidad interpretables y confiables para predicciones individuales de IA en aplicaciones médicas.

Principales métodos:

  • El LPV estima la fiabilidad de la predicción analizando la frecuencia de corrección dentro de los vecindarios de puntuación de confianza.
  • El CPV refina el LPV utilizando un enfoque bayesiano, incorporando valores predictivos globales como priors para una distribución de probabilidad de corrección posterior.
  • El marco se aplicó a conjuntos de datos de imágenes médicas de referencia.

Principales resultados:

  • El LPV y el CPV generaron estimaciones de fiabilidad adaptativas localmente e interpretables para las predicciones de IA.
  • Las métricas identificaron con éxito instancias donde la evidencia local era insuficiente o engañosa.
  • El suavizado bayesiano en CPV demostró una estabilidad mejorada contra datos locales escasos o engañosos.

Conclusiones:

  • El marco LPV y CPV mejora la interpretabilidad y la confiabilidad de los sistemas de IA médica a nivel de caso individual.
  • La combinación de la calibración local con la inferencia bayesiana ofrece un enfoque robusto para evaluar la fiabilidad de las predicciones de IA.
  • Estas métricas son cruciales para avanzar en el desarrollo de IA confiable en la atención médica.