Deciphering human faces with artificial intelligence for healthcare

IF 0.5 4区医学 Q4 PSYCHIATRY

Annales medico-psychologiques Pub Date : 2024-11-01 DOI:10.1016/j.amp.2024.09.011

Antitza Dantcheva

{"title":"Deciphering human faces with artificial intelligence for healthcare","authors":"Antitza Dantcheva","doi":"10.1016/j.amp.2024.09.011","DOIUrl":null,"url":null,"abstract":"<div><h3>Context</h3><div>At a time of a rapid growth in the population of elderly individuals and at a time of decreased/pressed availability of human healthcare-resources, automated face analysis has the potential to offer efficient and cost-effective methods for monitoring of a number of pathologies.</div></div><div><h3>Objectives</h3><div>The author revisits works in automated face analysis, which have focused on designing computer vision algorithms deducing the health state of individuals. Current limitations and benefits are discussed, placing emphasis on the potential that such technology can bring.</div></div><div><h3>Methods</h3><div>Computer vision algorithms, most recently based on deep neural networks have been trained with facial images or videos, jointly with health state annotations from clinical experts, in order to learn such algorithms to deduce facets of health states. Examples of such notable algorithms include approaches detecting stress, depression, apathy, pain, neurological disorder, as well as classification of expressions and phenotypes of genetic disorders.</div></div><div><h3>Conclusions</h3><div>Such algorithms are evolving rapidly, providing increasingly reliable accuracy and can support clinicians by providing objective measures.</div></div>","PeriodicalId":7992,"journal":{"name":"Annales medico-psychologiques","volume":"182 9","pages":"Pages 882-884"},"PeriodicalIF":0.5000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annales medico-psychologiques","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0003448724002968","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"PSYCHIATRY","Score":null,"Total":0}

引用次数: 0

Abstract

Context

At a time of a rapid growth in the population of elderly individuals and at a time of decreased/pressed availability of human healthcare-resources, automated face analysis has the potential to offer efficient and cost-effective methods for monitoring of a number of pathologies.

Objectives

The author revisits works in automated face analysis, which have focused on designing computer vision algorithms deducing the health state of individuals. Current limitations and benefits are discussed, placing emphasis on the potential that such technology can bring.

Methods

Computer vision algorithms, most recently based on deep neural networks have been trained with facial images or videos, jointly with health state annotations from clinical experts, in order to learn such algorithms to deduce facets of health states. Examples of such notable algorithms include approaches detecting stress, depression, apathy, pain, neurological disorder, as well as classification of expressions and phenotypes of genetic disorders.

Conclusions

Such algorithms are evolving rapidly, providing increasingly reliable accuracy and can support clinicians by providing objective measures.

查看原文本刊更多论文

利用人工智能破译人脸，促进医疗保健

背景随着老年人口的快速增长和人类医疗资源的减少/紧张，自动人脸分析有可能提供高效且具有成本效益的方法来监测一些病症。方法最近基于深度神经网络的计算机视觉算法已通过面部图像或视频以及临床专家的健康状态注释进行了训练，以便学习这种算法来推断健康状态的方方面面。此类著名算法的例子包括检测压力、抑郁、冷漠、疼痛、神经紊乱的方法，以及遗传疾病的表情和表型分类。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Annales medico-psychologiques 医学-精神病学

CiteScore

1.30

自引率

33.30%

发文量

196

审稿时长

4-8 weeks

期刊介绍： The Annales Médico-Psychologiques is a peer-reviewed medical journal covering the field of psychiatry. Articles are published in French or in English. The journal was established in 1843 and is published by Elsevier on behalf of the Société Médico-Psychologique. The journal publishes 10 times a year original articles covering biological, genetic, psychological, forensic and cultural issues relevant to the diagnosis and treatment of mental illness, as well as peer reviewed articles that have been presented and discussed during meetings of the Société Médico-Psychologique.To report on the major currents of thought of contemporary psychiatry, and to publish clinical and biological research of international standard, these are the aims of the Annales Médico-Psychologiques.