DOTmed Home MRI Oncology Ultrasound Molecular Imaging X-Ray Cardiology Health IT Business Affairs
News Home Parts & Service Operating Room CT Women's Health Proton Therapy Endoscopy HTMs Mobile Imaging
SEARCH
Posição atual:
>
> This Story


Início de uma sessão ou Registo to rate this News Story
Forward Printable StoryPrint Comment

 

 

Health IT Homepage

Healthix adopts Verato solution for patient matching, waives HIE connection fee Largest public health information exchange in the US

Tech giants sign on to interoperability pledge Amazon, Google, IBM, Microsoft, Oracle, and Salesforce agree to common interest

Research team uncovers 20 security flaws in widely used EHR software Left data of millions worldwide vulnerable to various cyberattacks

Bringing a higher standard to standardization at AAMI Saved Care New England over $650,000, continuing standardization there

REAL Radiology acquires Argus Radiology Consultants Aligns two 100 percent radiologist owned-and-operated organizations

Daphne Jones AMN Healthcare Board appoints new independent director

Value-based care is here: How health IT can help Identify the gaps in your data and analytics and begin to raise the bar

Varian to acquire humediQ Global Bringing IDENTIFY automated workflow solution to surface-guided radiation therapy

Brian Tyler McKesson appoints president and chief operating officer

In the ED, best-of-breed solutions preferred over enterprise EHRs Black Book research cites functionality and usability

Study team tricks AI programs into misclassifying diagnostic images

por John W. Mitchell , Senior Correspondent
With machine learning algorithms recently approved by the FDA to diagnose images without physician input, providers, payers, and regulators may need to be on guard for a new kind of fraud.

That’s the conclusion of a Harvard Medical School/MIT study team comprising biometric informatics, physicians, and Ph.D. candidate members, in a paper just published in IEEE Spectrum. The team was able to successfully launch “adversarial attacks” on three common automated AI medical imaging tasks to fool the programs up to 100 percent of the time into misdiagnosis. Their findings have imaging implications related to fraud, unnecessary treatments, higher insurance premiums and the possible manipulation of clinical trials.

Story Continues Below Advertisement

THE (LEADER) IN MEDICAL IMAGING TECHNOLOGY SINCE 1982. SALES-SERVICE-REPAIR

Special-Pricing Available on Medical Displays, Patient Monitors, Recorders, Printers, Media, Ultrasound Machines, and Cameras.This includes Top Brands such as SONY, BARCO, NDS, NEC, LG, EDAN, EIZO, ELO, FSN, PANASONIC, MITSUBISHI, OLYMPUS, & WIDE.



The team defined adversarial attacks on AI imaging algorithms as: “…inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake."

“Adversarial examples have become a major area of research in the field of computer science, but we were struck by the extent to which our colleagues within healthcare IT were unaware of these vulnerabilities,” Dr. Samuel Finlayson, lead author and M.D.-Ph.D. candidate, Harvard-MIT told HCB News. “Our goal in writing this paper was to try to bridge the gap between the medical and computer science communities, and to initiate a more complete discussion around both the benefits and risks of using AI in the clinic.”

In the study, the team was able to manipulate the AI program to indicate positive findings in pneumothorax noted in chest X-rays, diabetic retinopathy observed in retinal mages and melanoma based on skin images. In the chest X-ray examples, the degree of accuracy based on the AI manipulation to indicate pneumothorax was 100 percent.

“Our results demonstrate that even state-of-the-art medical AI systems can be manipulated,” said Finlayson. “If the output of machine learning algorithms becomes a determinant of healthcare reimbursement or drug approval, then adversarial examples could be used as a tool to control exactly what the algorithms see.”

He also said that such misuse could cause patients to undergo unnecessary treatments, which would increase medical and insurance costs. Adversarial attacks could also be used to “tip the scales” in medical research to achieve desired outcomes.

Another member of the study team, Dr. Andrew Beam, Ph.D., instructor, Department of Biomedical Informatics, Harvard Medical School believes their findings are a warning to the medical informatics sector. While the team stated they were excited about the “bright future” that AI offers for medicine, caution is advised.

"I think our results could be summarized as: 'there is no free lunch'. New forms of artificial intelligence do indeed hold tremendous promise, but as with all technology, it is a double-edged sword,” Beam told HCB News. “Organizations implementing this technology should be aware of the limitations and take active steps to combat potential threats.”

Health IT Homepage


You Must Be Logged In To Post A Comment

Anuncie
Aumente a Sua Perceção da Marca
Leilões + Vendas Privadas
Comece
O mais melhor preço
Comprar Equipamento/Peças
Encontre
O preço o mais baixo
Notícia diária
Leia
A notícia a mais atrasada
Diretório
Browse tudo
DOTmed Usuários
Ética no DOTmed
Veja o nosso
Programa das éticas
O ouro parte o programa do vendedor
Receba PH
Pedidos
Programa do negociante do serviço do ouro
Receba RFP/PS
Pedidos
Fornecedores de Healthcare
Veja tudo
Ferramentas de HCP
Trabalhos/Treinamento
Achado/suficiência
Um trabalho
Parts Hunter +EasyPay
Comece as peças
Citações
Certificado recentemente
Vista recentemente
Usuários certificados
Recentemente Rated
Vista recentemente
Usuários certificados
Central Rental
Equipamento do aluguel
Para menos
Vender Equipamentos/Peças
Comece
A maioria de dinheiro
Preste serviços de manutenção ao Forum dos técnicos
Ajuda do achado
E conselho
Simples RFP
Comece o equipamento
Citações
Mostra de comércio virtual
Serviço do achado
Para o equipamento
O acesso e o uso deste local são sujeitos aos termos e às condições do nosso OBSERVAÇÃO LEGAL & OBSERVAÇÃO DA PRIVACIDADE
Propriedade de e proprietário DOTmeda .com, Inc. Copyright ©2001-2018 DOTmed.com, Inc.
TODOS OS DIREITOS RESERVADOS