Lifeline Biotechnologies Inc (LLBO)

[tonyb2232]

French Article "Will artificial intelligences beat cancer?"

https://www.esanum.fr/today/posts/les-intelligences-artificielles-vaincront-elles-le-cancer

Joris Galland is a specialist in internal medicine. After having worked at the Lariboisière hospital (AP-HP) he joined the CH Bourg-en-Bresse. Passionate about new technologies, he proposes in our blog " Connexion (s) " to explain the issues to us.
Cancer is the second leading cause of death in the world. With 8.8 million deaths in 2015, it is responsible for nearly one in 6 deaths. 1 In France, the overall number of new cancer cases has been increasing every year for the past thirty years. In question, the extension of life expectancy (explosion of cases of breast or prostate), behavioral and environmental factors but also the improvement of diagnostic methods.

Cancer is for some the failure of modern medicine . However, medicine has made significant progress in cancer screening (PSA assay), their diagnosis and targeted treatments of neoplastic cells. In the space of half a century, scientific research has succeeded in significantly improving the prognosis of certain cancers with the advent of biotherapies and gene therapies. Without forgetting the major role of prevention and / or screening campaigns. Artificial Intelligence (AI) is expected to revolutionize oncology in the next ten years. Here's how.


Pixels and "wearables"
Early detection of cancer is essential for improving the prognosis. The speed of diagnosis in imaging is already revolutionized by AI. While it takes ten years of training for a human brain to learn radiology, an AI from Google manages to dethrone the best radiologists in the diagnosis of lung cancer after only a few days of training. 2

Finally, what could be easier for an AI? The computer can image pixel by pixel, the human eye and brain cannot. Thanks to its analytical precision and deep learning, AI becomes an ally of the radiologist. In 2019, in the journal Nature , a team of researchers presented an algorithm for predicting the risk of lung cancer from low-dose CT images. When no previous image was available, the AI ??did better than the radiologist with a 5% reduction in false negatives.

Connected clothing (or wearables ) is another innovation, at the crossroads of the Internet of Things and AI. Do you know the bra that detects breast cancer? The American laboratory Cyrcadia offers a prototype called iTbra ™. This gilet-bra allows the detection of breast cancer at early stages with at least as much sensitivity as a mammogram. 3

Comprised of two smart breast patches placed in a bra, this wearable identifies temperature changes in breast tissue. Machine learning predictive analytics AI helps identify and classify abnormalities in breast tissue. In the event of an abnormality, the system will warn the patient to go see a doctor to perform the appropriate imaging examinations. The first results are promising and certification is in progress.

If this system is so good, why not use the same technology with a connected underwear that would detect cancer of the genitals? Or a T-shirt that would detect the presence of tumor? It sounds like science fiction, but the field of wearable is making great strides . The Hexoskin 4 t-shirt can already assess the patient's vital parameters, respiratory volumes, quality of sleep, etc. The device has been tested in Covid-19 patients, as part of home rehabilitation or in research work.


The contributions of the genome
The hope of oncologists does not rest only on the very early diagnosis of the first cancer cells. Ideally, this would be to improve the prediction of cancer , even before the formation of the first cancer cell. This is where advances in genetics come in.

In the 1990s, top researchers claimed that the human genome would never be sequenced, or not for hundreds of years. Advances in computer science have made this feat possible: some machines only need four hours to sequence the entire human genome and for only a few hundred dollars (this is called “NGS”, for Next Generation Sequencing ). In the next ten years, the sequencing speed is expected to improve exponentially and at modest costs.

If the sequencing of the genome is no longer a problem, the interpretation of the masses of data generated becomes problematic. No geneticist is able to interpret this flow of information. This is where AI comes in. A large genomic study carried out on nearly 10,000 women with ovarian cancer identified a common genetic variant that increases the susceptibility to tumor occurrence by 20. at 40%. 5 With NGS, it would be possible to screen for this variant in women, from birth, and to offer them close follow-up if necessary. We are no longer far from the world of the film Bienvenue à Gattaca ; a legal framework becomes essential.


From pharmacovigilance to relapse detection
AI allows, among other things, the analysis of big data. They have the ability to make links between a risk factor and cancer, even though the human brain would not have thought of it . For example, an AI has highlighted the link between the drug pioglitazone (antidiabetic) and bladder cancer, leading to withdrawal of the drug. If this algorithm, which only takes a few minutes to train, were deployed on a large scale, it would allow a real revolution in pharmacovigilance with the detection of side effects in near real time.

One of the roles of the oncologist is to predict and diagnose the risk of relapse of cancer in remission: here again, new technologies will be of great help. The MOOVCARE POUMON application is an application that detects a potential relapse of lung cancer. 6 Every week, it analyzes the evolution of symptoms using a questionnaire completed by the patient.

This application uses an algorithm that achieves a relapse detection sensitivity close to 100%. Above all, these can be detected five to six weeks earlier than scanners, conventionally performed every three months. The referring oncologist is then directly alerted. Tests are under study for breast cancer, kidney cancer, prostate cancer and lymphoma. Thanks to its efficiency and the actual benefit, the application is validated by the HAS and supported by social security.


A market opening up to web giants
This list of connected health projects in oncology is not exhaustive. Many other start-ups are constantly working to improve the prediction, early detection, diagnosis and treatment of cancers. The determining element, for these companies, is the collection of big data. This factor is not limiting for American GAFAMI or Chinese BATX. The giants of the web are therefore interfering more and more in the field of cancerology.

As we have seen, IBM is starting to diagnose rare cancers and identify the best treatment thanks to its super AI Watson . For its part, the biotechnology laboratory of Google X, named "CALICO", would work secretly on a project of Immortal Man, via the famous "DNA scissors" CRISPR-Cas9. The idea here is to increase humans by modifying their DNA so that they no longer fall ill. Once again, the establishment of a legal framework becomes urgent, if we do not want to fall into eugenics.

Google is also working on a nanoparticle that could diffuse into the blood in order, for example, to find cancer cells or fight them. This nanoparticle could even communicate directly with the person's watch to alert them in case of discovery of a disease. 7

Tencent, the Chinese multinational which operates the WeChat messaging application in particular, wanted to position itself in force. In 2017, it launched Artificial Intelligence Medical Innovation System (AIMIS), a medical imaging system based on artificial intelligence. AIMIS allows the screening of several diseases, including diabetic retinopathy and certain cancers. The system, currently undergoing clinical validation in around 100 hospitals in southern China, has enabled doctors to analyze more than 100 million images. According to the company, the image recognition accuracy rate is 90% for esophageal cancer and 97.2% for colorectal cancer. The punching power of these giants, while unfair to small businesses, will undoubtedly allow for dramatic advances in oncology.

And you what do you think ? Will cancer soon be a rare disease thanks to AI?