Teach a Computer to Recognize AML

Researchers have developed the first computer machine-learning model to accurately predict which patients diagnosed with acute myelogenous leukemia, or AML, will go into remission following treatment for their disease and which will relapse. The computer was trained using bone marrow data and medical histories of AML patients, as well as blood data from healthy individuals. Cases about which the computer had no information were evaluated by the algorithm by applying knowledge about similar cases in the database. The computer was then able to predict remission with 100 percent accuracy. Relapse was correctly predicted in 90 percent of relevant cases.

"It's pretty straightforward to teach a computer to recognize AML, once you develop a robust algorithm, and in previous work we did it with almost 100 percent accuracy," said Murat Dundar, senior author of the disease-progression study and associate professor of computer science in the School of Science at Indiana University-Purdue University Indianapolis. "What was challenging was to go beyond that work and teach the computer to accurately predict the direction of change in disease progression in AML patients, interpreting new data to predict the unknown: which new AML patients will go into remission and which will relapse."

"As the input, our computational system employs data from flow cytometry, a widely utilized technology that can rapidly provide detailed characteristics of single cells in samples such as blood or bone marrow," explained Bartek Rajwa, first author of the study and research assistant professor of computational biology in the Bindley Bioscience Center at Purdue University. "Traditionally, the results of flow cytometry analyses are evaluated by highly trained human experts rather than by machine-learning algorithms. But computers are often better at extracting knowledge from complex data than humans are."

Automated measurement and monitoring of response to treatment of AML are critical not only for objective evaluation of disease-status prognosis but also for timely assessment of treatment strategies, the study's authors noted. Their work creates and underlies a clinical decision support system that recognizes the presence of minute residual amounts of malignant cells of any AML type in bone marrow samples, enabling early identification of change in direction of disease progression.

"Machine learning is not about modeling data. It's about extracting knowledge from the data you have so you can build a powerful, intuitive tool that can make predictions about future data that the computer has not previously seen - the machine is learning, not memorizing - and that's what we did," said Dundar, an internationally respected machine-learning scientist who specializes in teaching computers to understand biomedical data.

The National Cancer Institute anticipated that 19,950 individuals would be diagnosed with AML in 2016 and forecast that approximately 10,430 deaths from AML would occur last year.

The study was a collaboration of IUPUI's Dundar and Purdue's Rajwa with Roswell Park Cancer Institute's Paul K. Wallace, a flow cytometry expert, and Elizabeth A. Griffiths, a physician who treats patients with AML.

This research, which has potential application to other hematological neoplasms in addition to AML, was supported by National Science Foundation grant IIS-1252648 (CAREER), by National Institute of Biomedical Imaging and Bioengineering grant 5R21EB015707 and in part by National Cancer Institute grant 5P30 CA01605. The content is solely the responsibility of the authors and does not necessarily represent the official views of NSF and NIH.

Rajwa B, Wallace PK, Griffiths EA, Dundar M.
Automated Assessment of Disease Progression in Acute Myeloid Leukemia by Probabilistic Analysis of Flow Cytometry Data. IEEE Trans Biomed Eng. 2016 Jul 13. doi: 10.1109/TBME.2016.2590950.

Most Popular Now

Interactive Health Apps May Inspire Heal…

Just like real doctors and nurses, online health tools with good - but controlled - communication skills can promote healthier lifestyles, according to researchers. However, if their tone is conversational...

Read more

Augmented Reality Visor to Dramatically …

Employing new photonics technology, European scientists are developing a new Augmented Reality surgical visor in a bid to improve accuracy of interventions, showing anaesthetic and medical data while superimposing a...

Read more

Call for Papers: EHB 2017 - IEEE Interna…

22 - 24 June 2017, Sinaia, Romania. The 6-th edition of the International Conference on e-Health and Bioengineering, EHB 2017, will take place in the city of Sinaia, Romania. This year...

Read more

UK and Italian Health Tech Firms to Help…

Data sharing ambitions set out in newly published sustainability and transformation plans (STPs) have been given a boost by a new strategic partnership between data management specialist Stalis and Italy's...

Read more

From Health Apps to Nursing Robots - A G…

25 - 27 April 2017, Berlin, Germany. Around the world the subject of e-Health is steadily gaining in importance, whether it involves electronic patient files, online video consultations or any of...

Read more

Philips Teams Up with German Startup One…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, today announced a partnership agreement with German digital health company Onelife Health to jointly develop innovative connected health...

Read more

EU eHealth Competition 2017

The eHealth Competition is an initiative that rewards the best eHealth / mHealth solutions produced by European SMEs (Small and Medium Enterprises). Its objective is to support business success of...

Read more

Philips and LabPON Plan to Create World…

Royal Philips (NYSE: PHG, AEX: PHIA) and LabPON, the first clinical laboratory to transition to 100% histopathology digital diagnosis, have announced its plans to create a digital database of massive...

Read more

Startupbootcamp Digital Health Berlin: C…

Startupbootcamp Digital Health Berlin supports innovative startups that combine medical knowledge with smart technologies, with special focus on behavior change, diagnostics and genomics, big data and analytics. Startupbootcamp provides mentorship...

Read more

Virtual Reality Cognitive Training Game …

Greek researchers demonstrated the potential of a self-administered virtual supermarket cognitive training game for remotely detecting mild cognitive impairment (MCI), without the need for an examiner, among a sample of...

Read more

Technology Boost for Health and Social C…

Health and social care organisations aiming to be fully compliant with the government’s Personalised Health and Care 2020 plan, can now access electronic health record (EHR) and healthcare integration technologies...

Read more

Philips Introduces Advanced Radiology So…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, has unveiled new advanced radiology solutions at the 2017 European Congress of Radiology (ECR). In response to today's...

Read more
(HEALTH IT) SPACE - Take a look at who has just Joined