TechSectors: Diagnostics - A Picture Says a Thousand Words

Publication
Article
MDNG PsychiatryAugust 2008
Volume 8
Issue 8

Next-generation decision support technology is designed to match the way a physician thinks about signs, symptoms, and diagnoses, facilitating rapid diff erential diagnosis generation.

Next-generation decision support technology is designed to match the way a physician thinks about signs, symptoms, and diagnoses, facilitating rapid diff erential diagnosis generation.

The considerable human costs and economic impact attributable to medical errors and high rates of misdiagnosis have eroded the public’s trust in the healthcare system. Some studies have found that up to 20% of medical diagnoses are incorrect. This can be attributed to several factors, including the nature of medical school training, fi nancially driven time pressures on doctors, a fragmented healthcare delivery system, and ever-increasing quantities of medical data. Th ere is simply too much to know and certainly too much for any primary care doctor to possibly memorize. Given this, why is diagnostic decision support technology so rarely used? Despite all the hand wringing about improving quality of care, this technology is often discussed but rarely implemented. Physicians cite complexity, cost, workfl ow diffi culties, and outright skepticism that clinical decision support works.

What can change this? This may seem simplistic, but current clinical decision support technologies are missing one element that counters all of these claims: pictures. Visual diagnostic decision support technology addresses the non-analytical, instantaneous perceptual moment that occurs when the doctor examines the patient, which can help improve the diagnostic process tremendously, considering that many diseases have a skin or pattern clue, and a signifi cant percentage of a general practitioner’s diagnosis is visually based.

The challenges of diagnosis

Medical errors due to physician orders and drug reactions grab headlines, but the more serious and underlying concern is misdiagnosis. The lack of attention accorded to diagnostic errors is due to the systemic and cultural complexities of reporting and collecting data on them. Yet, diagnostic error often initiates a cascade of subsequent errors—failure to use an indicated diagnostic test, misinterpretation of test results, failure to act on abnormal results, and incorrect treatment. Physicians are taught a highly structured cognitive method in medical school, and they habituate this methodology throughout their training and subsequent practice. Medical education stresses memorization of basic science and clinical facts; this means that students must focus on prototypical “classic cases” rather than learn all the variants. As the medical student moves from the classroom to residency, training shifts to “practice-based” learning from unique clinic or hospital patient cases.

These residents soon realize that most patients do not neatly present as the textbook suggests. Th us, the life-long learning of the physician begins. Expertise evolves from interaction with thousands of patients, learning from the twists and turns of each individual case, synthesizing and remembering the vast array of symptom and examination patterns over a career. Our patients hope we have this expertise and assume if we are early in our careers that we have developed a methodology to think about, recognize, and diagnose their problem regardless of how much experience we actually have. Yet, a great number of patients will appear in our offices with patterns we have never seen in practice or read about in texts. Practitioners of family, internal, pediatric, or emergency medicine are expected to recognize patterns and make diagnoses that span all of the medical specialties. The frequent variants of common and rare diagnoses might be diffi cult for these non-specialty physicians

to recognize, even after 20 years of practice.

Many physicians readily admit they are insuffi ciently trained to recognize visual and skin or pattern-recognition-based clues that can assist in making a diagnosis. Th is challenge is compounded every day in fast-paced clinics, emergency rooms, and hospitals, where generalists are forced to make quick decisions, often with incomplete data and a dearth of experience in evaluating the subtleties of disease characteristics.

Building better efficacy: The value of visuals

Diagnostic decision support systems, though rarely used, allow physicians to enter a patient’s symptoms, lab results, and other data to build a textbased collection of diagnostic possibilities. However, current diagnostic systems limit the dynamic nature of medical diagnosis and do not allow for the incorporation of perceptual and visual data into clinical thinking. Many physicians fi nd it diffi cult to describe the visual clues and patterns they observe, and extensive text on a page or screen makes it diffi cult to recognize patterns of disease.

There is a great need in medicine for a better visual approach to pattern recognition. The visual diagnostic decision support system (VDDSS) meets this need because it was designed to match the way a physician thinks about signs, symptoms, and diagnoses. It allows rapid visual and iconic search and entry of visual patient clues and presents multiple images and graphics of each disease alternative, demonstrating how each might look at different stages and in people of diff erent ages and ethnicities.

The difference between perception and cognition is a key differentiator between VDDSS and non-visual diagnostic decision support systems. In contrast to prior efforts in diagnostic decision support, the database interface and information management strategy used with VDDSS facilitate rapid comparisons and visual diff erential diagnosis generation. Many internal diseases present with visual clues that can be used as a leveraging tool when making a diagnosis. These objective clues and signs of internal disease often go unrecognized and uninterpreted by primary care clinicians, resulting in delayed diagnosis and reduced quality of care. VDDSS uses search technology that requires data entry of patient symptoms, complaints, and other factors, providing a way to both narrow the scope of search results and simultaneously sort through a multitude of images to show not just the most common visual, but an image that is closest to the morphology entered by the user.

Combined with a purposefully designed visual display, image variants can be displayed to assist the user in recognition. While the human brain has remarkable innate abilities to pattern-match between like images, databases can more easily catalog variation. Until now, our human-computer interfaces in medicine have not been optimized to facilitate simultaneous pattern matching and differential diagnosis generation. By entering and selecting a patient’s findings as a combination of text and

images, clinicians can build a customized pictorial differential diagnosis in seconds, drawn from thousands of medical photographs and revealing the variation in presentation between—as well as within—diseases.

VDDSS solutions bring decision support to new levels of efficacy. The unusual variants of the common, as well as the rare, diagnoses are often difficult for the non-specialist to recognize because of broad training necessarily focused on prototypical “classic cases” across a wide area of medicine. Information tools that allow physicians to enter patient factors and perceptual and visual data provide powerful benefits for achieving more in-depth knowledge and diagnostic acuity. Visuals and data allow diagnosticians the best of both worlds: a superior technological synthesis of complex data along with the physician’s clinical

judgment.

Art Papier, MD, is a practicing dermatologist, associate professor in Dermatology and Medical Informatics at the University of Rochester School of Medicine and Dentistry, and Chief Medical Officer and co-founder of Logical Images, a visual diagnostic decision support company in Rochester, NY. For more information, please visit www.logicalimages.com.

Related Videos
Rebecca A. Andrews, MD: Issues and Steps to Improve MDD Performance Measures
A Voice Detecting Depression? Lindsey Venesky, PhD, Discusses New Data
Daniel Karlin, MD: FDA Grants Breakthrough Designation to MM120 for Anxiety
Leesha Ellis-Cox: Steps to Closing the Bipolar Disorder Diagnosis Gap for Blacks
Daniel Greer, PharmD: Reduction in Rehospitalizations with Antipsychotic Injections for Schizophrenia
Understanding the Link Between Substance Use and Psychiatric Symptoms, with Randi Schuster, PhD
Andrew Miller, PhD: Inventor of KarXT Discusses Pivotal EMERGENT-2 Data
© 2024 MJH Life Sciences

All rights reserved.