• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

Researchers Identify Top 3 Misdiagnosed Conditions


But tech could help reduce deadly diagnostic errors.

misdiagnosis,diagnostic error,clinical decision support,diagnosis

Diagnostic errors are the most common, catastrophic and expensive clinical mistakes. Most alarming, medical errors are the third leading cause of death in the U.S. Now, researchers have identified three major disease categories — vascular events, infections and cancers — that account for nearly 75% of all serious harms from diagnostic errors, according to a paper published in the journal Diagnosis.

Clinical decision support tools and other technology, however, could help improve the situation.

The research team, led by David Newman-Toker, M.D., Ph.D., director of the Johns Hopkins Armstrong Institute Center for Diagnostic Excellence, discovered that diagnostic errors that led to death or permanent disability were associated with misdiagnosed cancers (37.8%), vascular events (22.8%) and infections (13.5%). The most frequent disease in each category was stroke, sepsis and lung cancer.

They also found that nearly half of the serious harms from diagnostic error are attributable to one of 15 disease states.

“Our findings suggest that the most serious harms can be attributed to a surprisingly small number of conditions,” Newman-Toker said. “It still won’t be an easy or quick fix, but that gives us both a place to start and real hope that the problem is fixable.”

Researchers analyzed all 11,592 diagnostic error cases from a list of open and closed U.S. malpractice claims documented between 2006 and 2015 in the national Comparative Benchmarking System database. The database includes information from 400 hospitals and represents more than 18,000 physicians across the U.S.

Researchers grouped the health conditions present in the claims based on a standard classification system to identify and rank top conditions.

“To my knowledge, grouping these codes together to identify the most common harms from diagnostic error had not been done before, but doing so gives us an ‘apples to apples’ comparison of the frequency of different diseases causing harms,” Newman-Toker said.

Nearly 50% of the high-severity harm cases studied resulted in patient death, while the other half resulted in permanent disability.

Claims data also revealed that failure of clinical judgement caused more than 85% of the misdiagnosed cases.

A majority (71.2%) of diagnostic errors associated with malpractice claims occurred in ambulatory settings — emergency departments (missed infections and stroke) or outpatient clinics (cancer-related).

“These findings give us a road map for thinking about what kind of problems we need to solve in which clinical settings,” Newman-Toker said.

But deploying computer-based diagnostic decision support tools could help mitigate some of the risk, the study authors wrote.

Artificial intelligence (AI)-enabled technology can track diagnostic errors to help clinicians get a handle on the problem. The diagnostic skills of the software have been compared to humans in countless studies, many of which found machine-learning algorithms as effective or better than humans.

A lack of interoperability between providers can also lead to diagnostic errors. If providers have access to more information from a variety of networks, they can incorporate more clinically relevant data into their records and treatment plans.

Get the best insights in digital health directly to your inbox.


Tackling the Misdiagnosis Epidemic with Human and Artificial Intelligence

Analytics & Machine Learning Expertise Drive Early Detection

Reinventing Clinical Decision Support

Related Videos
Image: Ron Southwick, Chief Healthcare Executive
George Van Antwerp, MBA
Edmondo Robinson, MD
Craig Newman
Related Content
© 2024 MJH Life Sciences

All rights reserved.