CONTRATA EL SERVICIO
+52 (55) 5420-1119
+52 (55) 5420-1154
+52 (55) 5420-1188
atencioncliente@notimex.com.mx
ventasnacionales@notimex.com.mx
informacionclientes@notimex.com.mx

CONTRATA EL SERVICIO
+52 (55) 5420-1119
+52 (55) 5420-1154
+52 (55) 5420-1188
atencioncliente@notimex.com.mx
ventasnacionales@notimex.com.mx
informacionclientes@notimex.com.mx

NTX E-BOOK

Descarga nuestro libro digital: Periodismo del siglo XXI. Tu opinión nos interesa.

NTX E-BOOK

Descarga nuestro libro digital: Las Agencias de
Noticias en la Era Digital. Tu opinión nos interesa.

2018-08-15   14:56:59   INGLÉS
Artificial intelligence would reduce toxic effects of drugs in brain tumors

Mexico, Aug. 15 (Notimex).- A group of scientists from the Massachusetts Institute of Technology (MIT) uses new machine learning techniques to reduce the toxic dose of drugs used in the treatment of patients with tumors in the brain or spinal cord.

Patients with this type of condition receive chemotherapy or radiotherapy, along with drugs for their control, and it is estimated that their life expectancy is not greater than five years. Glioblastoma is a type of carcinoma (malignant tumor).

In a statement from MIT, the experts said that the pharmaceutical products administered in these cases generate debilitating side effects in patients.

The research seeks to improve the quality of life of people with glioblastoma, a more aggressive form of brain cancer, using the artificial intelligence model, which could make dosage regimens less toxic.

The method used by researchers at the MIT Media Lab is powered by a "self-learning" method, which analyzes current treatment regimens and adjusts doses interactively.

That is how it finds an optimal treatment plan, with the lowest potency and frequency of doses that should reduce the size of the tumors, to a degree comparable to traditional methods.

For the development of the research, the scientists made simulated trials to 50 patients, the model designed individual treatment cycles that reduced the potency to a quarter or half of almost all doses.

The trial maintained the same potential for tumor reduction, in addition, in some cases it omitted the doses completely, where it programmed administrations twice a year instead of monthly.

"We kept the goal, where we have to help patients by reducing tumor sizes, but, at the same time, we want to make sure that quality of life does not produce overwhelming disease and harmful side effects," said Pratik Shah, one of the supervisors of the study.

For the realization of the model, the researchers relied on the technique of reinforced learning, a method inspired by the psychology of behavior, where a model learns to favor certain behavior that leads to a desired result.

The scientists adapted a model of reinforced learning technique for glioblastoma treatments that use a combination of the drugs temozolomide and procarbazine, lomustine and vincristine, administered for weeks or months.

 

 

 

NTX/ICB/LCH/BBF

462 1