New software method for producing medical guidelines

Medical guidelines that lay down state-of-the-art rules for doctors are an important tool in modern medical practice. But though the number of guideline documents has proliferated in recent years, the quality, clarity and overall usefulness of the texts could be improved, resulting in even greater benefit to patients and medical practitioners.

A team of European researchers working on the IST-funded Protocure II project set out to do just that, developing a method to make guidelines not only more accurate and useful to doctors, but also far easier for national healthcare authorities to generate and update. Most strikingly, they did it by looking at guidelines not as simple texts, but as modular software programs that can be written in a programming language.

"In an earlier project, Protocure I in 2002, we analysed medical guidelines and determined that they can be written in a formal way using a programming language, then verified by computer to eliminate inconsistencies, repetitions and other flaws. In Protocure II we created the tools to translate the guidelines into a programming language, verify them and keep them up to date," explains project coordinator Mar Marcos of the Universitat Jaume I in Spain.

Turning guideline creation into a software process
In essence, the researchers in Protocure I likened the guideline to a computer program. In Protocure II, which ended in June 2006, they took that analogy a step further by likening guideline creation to software engineering.

A key outcome of the project is a process for translating raw text guidelines into machine-readable and machine-verifiable languages based on XML. This process is strongly supported by an interactive guideline mark-up tool named Delta.

"Delta allows us to track the whole transformation process, which can be crucial for incorporating changes made to the original guideline texts," Marcos says. The project partners also make use of KIV, a software verification system that enables them to check the transformed guideline against a set of generic rules that are common to all guidelines.

The Protocure II system was tested successfully on a guideline for treating breast cancer, which had been developed by one project partner, the Dutch Institute for Healthcare Improvement (CBO).

By making guideline development more efficient and less prone to errors, the researchers’ efforts promise considerable benefits for the national healthcare authorities and institutes that draft guideline documents. With Protocure II’s method their texts, which can sometimes run to 200 pages, should have fewer inconsistencies, making them of greater value to doctors and healthcare coverage planners.

Toward "living guidelines"
With the system making guideline contents easier to update, specialised healthcare organisations will be able to update the guidelines faster to keep pace with new technologies, new drugs and the results of clinical trials. According to the team, Protocure II could underpin the development of true "living guidelines", which change as fast as medicine advances.

Using a programming language as a basis for such guidelines also enables them to be used as a relatively simple decision-support system for doctors, further increasing their value to the medical community.

But despite the evident potential of the Protocure II tools, Marcos admits that deployment of the system would represent a major change from existing practice for the health institutes that draft guidelines. Nonetheless, the work of the project generated considerable interest at the October 2006 eChallenges conference in Barcelona.

A further obstacle at present is that the system has to be implemented and the transformation of guidelines carried out by IT specialists. However, Marcos says that one of the possibilities the Protocure II partners are considering is a way to support the implementation of guidelines, possibly within a future European research project.

Contact:
Mar Marcos
Department of Computer Engineering and Science
Universitat Jaume I
Campus de Riu Sec
E-12071 Castellon
Spain
Tel: +34 964 728 288
Fax: +34 964 728486
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Source: IST Results Portal

Most Popular Now

ChatGPT can Produce Medical Record Notes…

The AI model ChatGPT can write administrative medical notes up to ten times faster than doctors without compromising quality. This is according to a new study conducted by researchers at...

Alcidion and Novari Health Forge Strateg…

Alcidion Group Limited, a leading provider of FHIR-native patient flow solutions for healthcare, and Novari Health, a market leader in waitlist management and referral management technologies, have joined forces to...

Can Language Models Read the Genome? Thi…

The same class of artificial intelligence that made headlines coding software and passing the bar exam has learned to read a different kind of text - the genetic code. That code...

Study Shows Human Medical Professionals …

When looking for medical information, people can use web search engines or large language models (LLMs) like ChatGPT-4 or Google Bard. However, these artificial intelligence (AI) tools have their limitations...

Advancing Drug Discovery with AI: Introd…

A transformative study published in Health Data Science, a Science Partner Journal, introduces a groundbreaking end-to-end deep learning framework, known as Knowledge-Empowered Drug Discovery (KEDD), aimed at revolutionizing the field...

Bayer and Google Cloud to Accelerate Dev…

Bayer and Google Cloud announced a collaboration on the development of artificial intelligence (AI) solutions to support radiologists and ultimately better serve patients. As part of the collaboration, Bayer will...

Shared Digital NHS Prescribing Record co…

Implementing a single shared digital prescribing record across the NHS in England could avoid nearly 1 million drug errors every year, stopping up to 16,000 fewer patients from being harmed...

Ask Chat GPT about Your Radiation Oncolo…

Cancer patients about to undergo radiation oncology treatment have lots of questions. Could ChatGPT be the best way to get answers? A new Northwestern Medicine study tested a specially designed ChatGPT...

North West Anglia Works with Clinisys to…

North West Anglia NHS Foundation Trust has replaced two, legacy laboratory information systems with a single instance of Clinisys WinPath. The trust, which serves a catchment of 800,000 patients in North...

Can AI Techniques Help Clinicians Assess…

Investigators have applied artificial intelligence (AI) techniques to gait analyses and medical records data to provide insights about individuals with leg fractures and aspects of their recovery. The study, published in...

AI Makes Retinal Imaging 100 Times Faste…

Researchers at the National Institutes of Health applied artificial intelligence (AI) to a technique that produces high-resolution images of cells in the eye. They report that with AI, imaging is...

GPT-4 Matches Radiologists in Detecting …

Large language model GPT-4 matched the performance of radiologists in detecting errors in radiology reports, according to research published in Radiology, a journal of the Radiological Society of North America...