Blog: Pathologists See Artificial Intelligence as Promising Diagnostic Tool – HITInfrastructure.com
- Pathologists believe that artificial intelligence (AI) can be used as an effective diagnostic tool to improve clinical workflow efficiency and quality assurance in pathology.
In fact, three-quarters of 487 pathologists reported being interested or excited about using AI as a diagnostic tool, according to a article by Canadian researchers published in the NPJ Digital Medicine journal.
Around 80 percent of pathologists polled predicted the introduction of AI technology in the laboratory within the coming decade.
“In diagnostic fields such as radiology and pathology, AI carries the potential to transform the clinical practice of physicians. In pathology specifically, AI-based diagnostic platforms may perform image analysis for tissue histology, analyse molecular outputs from diagnostic tests such as next-generation sequencing (NGS), and integrate these with clinical and/or radiological characteristics to improve the predictive and prognostic power of traditional pathology approaches,” article explained.
The researchers observed that differences in perspectives about AI across specialties could impact the rate and effective of AI implementation. Clarifying these differences will help take the priorities of stakeholders into account.
“Specifically, pathologists’ concerns about impacts on job security, ability to adapt to novel technologies, and impact on clinical and research careers can be more effectively addressed by hospitals and pathology departments if they are well understood,” the researchers observed.
The researchers’ survey of 487 pathologists shed light on these concerns.
One in five worried about AI job displacement
Around 20 percent of respondents said they were concerned or extremely concerned that AI would displace jobs, while 17 percent expressed concern that AI would affect compensation.
Close to 41 percent of respondents said that adoption of AI would be welcomed by their colleagues, while 44 percent did not think AI adoption would have any impact on their relationship with colleagues.
A majority of respondents believed that patients would have no opinion on AI tools, while 29 percent said patients would be excited about AI tools.
Many respondents felt that with appropriate training, AI tools could significantly increase diagnostic efficiency in pathology.
Half of respondents said that AI implementation would permit increased research productivity and allow pathologists to answer questions that were previously not possible to answer.
Many respondents expressed concerns about unpredictable results or artefact-related errors from the use of AI tools. At the same time, a majority of respondents said that the use of AI-tools combined with human inputs for generation of diagnostic reports would help to decrease the rates of reporting errors.
A recent article in the Journal of Pathology and Translational Medicine by Korean researchers noted that deep learning is increasingly being used to advance the field of pathology by using clinical, radiologic, and genomic data to diagnose diseases and predict patient prognoses.
“The pathologic field in AI is expanding to disease severity assessment and prognosis prediction. Although most AI research in pathology is still focused on cancer detection and the grading of tumors, pathological diagnosis is not simply a morphological diagnosis, but is a complex process of evaluation and judgment of various types of clinical data that deal with various organs and diseases,” the article observed.
Healthcare AI market to grow at 41% CAGR
Factors driving this growth included the increasing application of artificial intelligence in the fields of drug discovery, medical imaging industry, precision medicine, and genomics.
The emergence of new applications for disease diagnosis and monitoring will further expand growth over the next few years.
Top healthcare AI vendors examined in the report include IBM, Google, NVIDIA, Microsoft, iCarbonX, Next IT Corp, CloudMex, Atomwise, Zephyr Health, Medtronic, Philips, and Oncora Medical.
North America and Europe are expected to have the largest market share of the overall market during the forecast period; however, emerging economies such as India and China are forecast to increase their market share over the long term.