GMV technology for securely sharing oncological-research and tumor-prediction information

Ahead of World Cancer Day the technology multinational GMV has made a big announcement: its inhouse development uTile now makes it possible for information on cancer patients to be shared without jeopardizing their privacy during research into new drugs and treatment. This GMV-developed cryptographic technology improves the precision of artificial-intelligence tumor-predicting techniques, reducing the need for biopsies. Hospitals, research centers and the pharmaceutical industry can now strike the right balance between harnessing healthcare data and respecting patient privacy, without exposing patient data to any risk of disclosure or even moving it from the respective health center.

Artificial intelligence (AI) has a huge potential for improving healthcare research, with a direct positive knock-on effect on patient wellbeing. Advanced analytical algorithms used to extract evidence from the great data universe generated by hospitals and clinical trials can draw conclusions capable of increasing the precision of disease diagnoses and prognoses. All this in turn helps to make healthcare professionals’ work more efficient, as they see their diagnoses borne out or fine-tuned with the data provided by this high-impact technology.

It is difficult for healthcare organizations to come by tools guaranteeing 100% anonymization of research data in the interests of collaborating with their peer organizations. As a result the clinical data of each health episode tends to get backed up in the so-called data silos of each hospital’s information systems. Even research at international level might turn out to be tricky because national bodies of law prevent the sharing of data outside each particular country. For these reasons aggregation of all this data is practically nonexistent as of today; this works against the much vaunted goal of interoperability.

Enter uTile: health data processing cryptography

Under Spain’s Digital Enabling Technologies program of the Economics and Enterprise Ministry, GMV has developed uTile PET (Privacy-Enhancing Technologies), a technological solution that makes calculations securely and in full privacy on patients’ distributed data, without exposing it to any risk of disclosure or even moving it from the hospital or health center concerned. This allows research centers and the pharmaceutical industry to tap into such crucial information as the survival rate: the value of biomarkers, prognoses, average patient age, etc., of clinical treatment without jeopardizing patient data privacy.

uTile harnesses confidential data in order to improve machine-learning algorithms and analytical models, complying at all times with organizational remits, data-privacy obligations and current law. The protection of personal data is a fundamental right recognized in article 18.4 of the Spanish Constitution and overlooked too by Europe’s General Data Protection Regulation (GDPR) and Spain’s Data Protection and Guarantee of Digital Rights Law (Ley Orgánica de Protección de Datos y Garantía de los Derechos Digitales: LOPDGDD), and further reinforced by the Patient Autonomy Law. All this legislation is binding on healthcare professionals, clinics, hospitals, medical centers and health institutions.

With uTile we no longer have to choose between data privacy and data harnessing. Advanced cryptographic methods keep the data encrypted while all necessary calculations are made. uTile hence guarantees that organizations’ sensitive data is never exposed or transferred through departments, organizations or different countries. Furthermore, data subjects do not even have to entrust their data to third parties. This data always remains protected behind the organization’s own internal controls, whether on-premise or in the cloud, and the sensitive information remains private throughout the whole calculation process.

uTile boosts the scope of current AI techniques, allowing them to be applied to separate data sources. Any AI clinical research project using uTile thus enjoys a crucial advantage: working with a bigger dataset taking in a huge sample.

Clinical applications of uTile

Some of them are the following:

• Boost the AI precision of current models predicting the presence of various tumors (prostate-, breast-cancer, etc) involving the use of MRI and other imaging techniques, cutting down the need for biopsies. uTile makes machine-learning images and data available without the need of sharing or moving it.
• Rare disease research. The clinical data of rare disease (RD) sufferers are scarce and scattered. Even with the National Rare Disease Registers, the amount of data is still limited. uTile brings into the trawl all available information held in local and national registers and also in European Reference Networks for rare diseases to discover hidden data relationships and respond to research queries.
• Patient-reported outcomes. In some cases symptoms associated with adverse results of medical treatment are not recorded in patients’ medical histories, so this information falls by the wayside. uTile represents a chance to record daily patient information using a smartphone and, without sharing information outside the patient/healthcare worker environment, using AI to improve and enlarge the set of knowledge on a given disease.