Research
Data science and childhood leukaemia


Published
3 years agoon


HT World reports on how data is helping to raise the prospect of better precision treatments for the disease.
A major collaborative project in the US is aiming to harness the power of data analytics to help physicians and researchers step up the fight against leukaemia.
Accenture, the professional services and tech giant, has built a model to manage and derive insights from data on paediatric acute myeloid leukaemia (AML).
The firm collaborated with researchers and clinicians from Fred Hutchinson Cancer Research Center (Fred Hutch), and the Target Pediatric AML (TpAML) computational working group.
The project aims to enable paediatric oncology physicians and researchers, specifically those focused on paediatric AML, to better analyse patient clinical trial and genetic data, with the potential to improve precision medicine.
In collaboration with the TpAML investigators, led by Dr. Soheil Meshinchi at Fred Hutch, Accenture data scientists aggregated and standardised genomic and clinical data from over 2,000 children with AML, treated in clinical trials.
RNA data alone, one of the most critical indicators of treatment outcomes in precision medicine, amounts to over 48,000 columns per patient if managed in a standard table format.
Combined with other relevant data points, such as patient demographics, clinical treatment arm, and prognosis, the sheer volume and variety of combinations presents a significant hurdle to comparing patient profiles and outcomes at scale.
“In this case particularly, I am pleased that we were able to leverage the power of data and analytics to make this information more accessible to researchers, potentially advancing precision medicine and helping improve people’s lives.”
Through this engagement, TpAML investigators provided access to the sequencing data and guidance on key data points, including genetic markers, clinical trial treatment details, and clinical outcomes, that can define a patient’s response to a particular treatment at the time of diagnosis (prior to the start of chemotherapy).
These insights could help inform the recommended course of treatment, giving patients and physicians a more robust view of likely clinical success and side effects with standard therapy, based on an individual patient’s genetic makeup and medical history.
This approach may provide a more informed pathway to more effective precision medicine for paediatric AML, where therapy might be modified based on patients’ predicted response to standard therapy. For example, high-risk patients may be allocated to bone marrow transplantation or targeted therapies.
“Integration of genomic and clinical data and getting it into a usable, accessible format is a significant challenge in precision medicine,” said Dr. Meshinchi.
“This collaborative effort between TpAML investigators and Accenture data scientists provides a mechanism to more informed analysis of clinical and genomic data, and could help identify patients at high risk of failure with conventional treatments. Validation of these findings can help modify patients’ treatments based on their relapse risk.”
By applying data science, engineering tools and machine learning to this corpus of information, Accenture has created a “code base that clinicians are using to model, understand and potentially predict how patients may respond to specific treatments”, the company says.
Data was made further accessible and consumable using 3D visualisation, offering a more interactive way to view the data in a “game-space environment, laying a foundation for advanced, dynamic visualisations and VR experiences which could help clinicians potentially identify anomalies, or which they could use as an interface to present findings”.
Stuart Henderson, global life sciences lead for Accenture, says: “For years, patients diagnosed with a disease often received the same treatment. And for some people, that treatment worked. However, for others, it did not work – or did so only marginally, or with serious side effects. With genome mapping, in combination with new analytical, scientific and technological advances, it is possible to develop targeted, more precise, personalised treatments for individuals or similar patient populations.
“Precision oncology is delivering on the promise of better patient care and health outcomes in remarkable ways and we look forward to seeing more projects like this TpAML investigation.”
60
SHARES


Healthcare innovators and leaders honoured at Imprivata HealthCon user group and awards ceremony


Wearable communication system may reduce digital health divide


Molecule trains the immune system to prevent cancer


Diabetes patients urged to use fitness games with caution


Urgent work needed to tackle ‘substantial’ digital health inequality


eSight: “The technology has the potential to change someone’s life”


Microsoft invests £2.5 billion in UK AI


TMS shows promise in tackling depression ‘epidemic’


AI depression app set for NHS clinical trial


UK Biobank releases world’s largest single set of sequencing data
Sign up for free updates from Health Tech World
Trending stories
- News3 weeks ago
Why a leading healthcare CEO sees recombinant DNA as a metaphor for developing breakthrough technologies
- AI6 days ago
AI model predicts breast cancer risk without racial bias
- Medtech4 weeks ago
Surtex Instruments to unveil game-changing Infinex microsurgery instruments at MEDICA
- AI2 weeks ago
Humans make better cancer treatment decisions than AI, study finds