Artificial intelligence to assist better myeloma care, is it the time?
| dc.authorid | 0000-0001-9636-4113 | |
| dc.contributor.author | Sevindik, Ömür Gökmen | |
| dc.date.accessioned | 2019-12-25T08:58:13Z | |
| dc.date.available | 2019-12-25T08:58:13Z | |
| dc.date.issued | 2019 | |
| dc.department | İstanbul Medipol Üniversitesi, Tıp Fakültesi, Dahili Tıp Bilimleri Bölümü, İç Hastalıkları Ana Bilim Dalı | |
| dc.description.abstract | Myeloma treatment made an enormous progress during the last decade. Armamentarium is grossly enlarging each year in the field of treatment. Parallel to the progress achieved to provide better care for myeloma patients, machine learning processes via artificial intelligence (AI) algorithms and big data analysis gained a remarkable progress. AI has rapidly diffused into various health sciences and cancer care also. Despite the advent of many efficacious treatment approaches and drugs, still we are not able to cure myeloma. Among the main limitations and barriers to cure, heterogeneity of phase 3 trials and lack ofwell organized and updated real life data are the ones that has to be addressed properly. Very recent and prestigous guidelines to provide evidence to a better myeloma care takes phase 3 randomized trials into account both in frontline and relapsed setting. Saying that frontline therapy is somehow standardized, relapsed setting is poorly organized among standardized recommendations for an individual myeloma patient. Regarding the heterogeneity of phase 3 trials and even published real life data,machine learning can possess an integrative approach to input individual patient data from datasets of randomized trials and wellestablished patient registries and to assist providing the best approach for an individual myeloma patient as an output via AI. We are now initializing our own nation-wide patient registry (Turkish Myeloma Patient Registry) system integrating machine learning process and planning to obtain assistance via training AI with patient specific demographic and disease related factors and efficacy and safety data of different treatment approaches as input variables and survival outcomes and patient reported outcomes as output variables, in a near future. We are also eager to co-operate with other national, multi-national databases and also the data providers of phase 3 randomized trials in the field to better optimize the artificial intelligence as an assistance tool in clinical decision making. | |
| dc.identifier.citation | Sevindik, Ö. G. (2019). Artificial intelligence to assist better myeloma care, is it the time? Clinical Lymphoma Myeloma & Leukemia içinde (E356-E356. ss.). https://doi.org/10.1016/j.clml.2019.09.588 | |
| dc.identifier.doi | 10.1016/j.clml.2019.09.588 | |
| dc.identifier.endpage | E356 | |
| dc.identifier.issn | 2152-2669 | |
| dc.identifier.issn | 2152-2650 | |
| dc.identifier.issue | 10 | |
| dc.identifier.startpage | E356 | |
| dc.identifier.uri | https://doi.org/10.1016/j.clml.2019.09.588 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12511/4674 | |
| dc.identifier.volume | 19 | |
| dc.identifier.wosquality | Q3 | |
| dc.indekslendigikaynak | Web of Science | |
| dc.language.iso | en | |
| dc.publisher | Cıg Media Group | |
| dc.relation.ispartof | Clinical Lymphoma Myeloma & Leukemia | en_US |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/embargoedAccess | |
| dc.subject | Artificial Intelligence | |
| dc.subject | Multiple Myeloma | |
| dc.subject | Real-World Data | |
| dc.title | Artificial intelligence to assist better myeloma care, is it the time? | |
| dc.type | Conference Object |
