Health quality data: an essential requirement for AI

Share
Share
23 NOVEMBER 2021

The cycle of sessions of the XI Conference R + D + I TIC Social Health 2021, contributed numerous examples of projects in the field of health and artificial intelligence (AI). The third session, held on October 27, began with a lecture by Xavier Ferràs, Professor of Operations, Innovation and Data Science at ESADE. In Ferràs’ opinion, AI has come to change the worldview. Its valuation was global providing the current geopolitical perspective: the two superpowers of China and the United States.

 

(Photo: from left to right, Karma Peiró (moderator), Xavier Ferràs, Anna Escalé, Carles Ramió, Carolina Garcia and Raimon Dalmau)

Anna Escalé, a primary care doctor at the EAP Navàs-Balsareny and SAP Bages-Berguedà-Solsonès, then spoke. She presented the pilot study of the use of AI as a support and diagnostic tool for skin lesions in primary care. “7.6% of the population consults annually for skin lesions. And this is one of the reasons why use the AI ​​tool. The initial hypothesis is that machine learning will allow us to diagnose faster and reduce unnecessary referrals to specialists, “Escalé explained.

Carles Ramió –Professor of Political Science at Pompeu Fabra University– focused his presentation on the aging of the population. “This fact will cause economic costs only in social and health care equivalent to 12% of Spanish GDP. This is unbearable,” he explained. In the opinion of this expert, AI can help balance this urgency. He also made it clear that it is just an instrument “that will have the capacity for public administrations to be able to take on”.

Carolina Garcia-Vidal – a senior specialist in Infectious Diseases at the Hospital Clínic de Barcelona – explained the experience of applying AI to improve real-time decision-making. Personalized medicine and data quality are the keys to the coming years. The success story was based on a classification of patient data with Covid-19 from Hospital Clínic in order to help doctors in a time of emergency. The experience has been transferred to a Belgian and a Dutch hospital.

Finally, Raimon Dalmau, head of the Information, ICT and Data Systems (CIO) Area of ​​the Medical Emergency System, spoke. In his presentation, he spoke about the advanced processing of data from the 061 Salut Respon and Urgent Health Transport services for the elaboration of predictive models that allow the optimization of resources in the health and logistics field.

Strategic organization

In the debate, the claim arose in public administrations to increase data governance. But also the need to train professionals in technical knowledge, budget investment for research in AI, perspective and time as well as confidence on the part of citizens.

“We lack a framework for political, legal and economic aid to Catalan healthcare,” said the Clínic researcher. “I can improve the quality of medical data.” In the ethical sense, Dalmau highlighted the issue of privacy of personal data because “there are tools of private company and the question is whether it is offered from a public health system.”

It was concluded that we are at a historic moment, where it is difficult to determine the boundary between technology and individual rights. All speakers agreed that we are in a revolution rather than just a transformation, which is expected to solve major current structural problems.

(See the full 3rd session at this link)

Strategies for adopting AI
The fourth and final session of the Conference took place on October 28. Josuè Sallent, Director of ICT Social Health, presented the Health / AI program of the ICT Social Health Foundation, and strategies for the adoption of AI in the sector. “We don’t want black boxes, we want tools capable of understanding how an AI has made a decision. We have to be absolutely transparent and give the maximum explanations. On the other hand, if we talk about algorithms we need system integration. health sector in the field of technology. In addition to the communication part, aimed at explaining very well to the public what we are doing “. According to Sallent, the Health / AI Program is being launched. And he appealed for criticism to improve it.

Then began a round of presentations of experiences and projects by the various speakers. Salvador Pedraza, territorial clinical director of radiology and nuclear medicine of the Hospitals of Girona; Juliana Ribera, COO of Amalfi Analytics; Pau Rodriguez, CEO of Methinks AI; Pere Romero, head of the ophthalmology service at the Sant Joan de Reus University Hospital; and David Reifs, technical director of Seidor’s innovation area and CEO of Skilled Skin (Clinicgram).

(Photo: from left to right, Josuè Sallent, Salvador Pedraza, Juliana Ribera, Karma Peiró, Pau Rodríguez, Pere Romero, David Reifs)

During the roundtable, priority challenges were questioned and emphasis was placed on current data and regulatory issues, such as issues of anonymity and transparency. Mention was made of the trust that technology companies have, but the existing fear that personal data will be used in the field of health.

It was recalled that AI should support healthcare professionals, and the machine can never be allowed to diagnose automatically. “The priority risk I see is how to solve a Rubik’s cube. You have one side that is regulation, the other is quality data, the other is investment, etc. And if you solve it, for it to work, it falls within the framework. of the legality, if you respect the ethical principles, you manage to explain it to the patients, and you convince the investors, because you have solved the cube. It is not easy “, commented in Pau Rodríguez.

It was concluded by prioritizing the knowledge of AI by the administrations to expedite bureaucratic processes, that Catalonia becomes a country of reference in the field of technology, that an entity dependent on the government covers all the needs of digitization, solvency of regulatory issues through the traceability of the procedure by a specialized body, and more cooperation between those skilled in the art.

With this session they ended the XI Conference R + D + I Tic Social Health 2021 –celebrated online during the days 20, 21, 27 and 28 October–, and organized by the Chair TIC Social Health of the University of Vic – Central University of Catalonia (UVic-UCC), the ICT Social Health Foundation (Department of Health of the Generalitat de Catalunya), the Vic Hospital Consortium, the Santa Creu de Vic Hospital Foundation, the EAP / ABS Centelles , the EAP Vic, the Catalan Institute of Health-Management Central Catalonia, Althaia Foundation and FORES. It is also sponsored by Seidor.

(See the full 4th session at this link)