Recommendation generation for performance improvement by using cross-organizational process mining

Download
index.pdf
2015
Kahveci, Mehmet Kubilay
Show full item record
103
views
34
downloads
Post marketing surveillance for pharmaceutical drugs has been largely dependent on spontaneous reporting systems (SRSs) for quite some time. Although paper based reporting forms are broadly replaced by digital (online) counterparts, accessibility and usability of those systems still pose problems. Considering the fact that adverse drug event (ADE) reporting is mostly a voluntary action and it takes a lot of effort to complete an ADE report on current systems, outputs are usually in low quality and quantity. On the other hand, individual case safety reports (ICSRs), generated by SRSs, contain contextual information such as patient's active medications, past medical history or past drug therapies, most of which is already available in patient's electronic health records (EHRs). Therefore, seamlessly accessing EHR sources to pre-fill ICSR forms would be a major improvement for spontaneous reporting process. There have already been studies aiming to utilize EHR data for post market surveillance. However, rather than focusing on facilitating the reporting process, they target automated detection of adverse events and to the best of our knowledge, none of them aims mobile platforms or has usability concerns for the end user. In this thesis, we address the issue of under-reporting and interoperability of those systems and demonstrate that EHR systems can be exploited in mobile SRSs to generate high quality reports at high rates and provide a better experience to the reporter as well. We have developed a scalable platform, integrable to existing reporting systems and EHR sources of different content models, which can semi-automatically pre-fill ADE reports using medical summary of patient available in EHR systems. The quality of reports produced using our tool and the amount of time spent reporting is a significant improvement compared to existing mediums.
Medical archives., Medicine, Drugs, Artificial intelligence
http://etd.lib.metu.edu.tr/upload/12619348/index.pdf
https://hdl.handle.net/11511/25004
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Semantic transformation framework to enable statistical research on medical summaries
Paçacı, Anıl; Altıngövde, İsmail Sengör; Doğaç, Asuman; Department of Computer Engineering (2015)
One of the important aspects of the clinical research studies carried out in the pharmacovigilance and pharmacoepidemiology is the postmarketing drug surveillance. Utilization of the available Electronic Health Record (EHR) data is key to complement and strengthen the postmarketing safety studies. In addition, EHRs provide a huge, but still under-utilized source of information for the observational studies in clinical research. However, use of different EHR data models and vocabularies presents an important...
Realizing drug repositioning by adapting a recommendation system to handle the process
OZSOY, Makbule Guclin; Ozyer, Tansel; Polat, Faruk; Alhajj, Reda (2018-04-12)
Background: Drug repositioning is the process of identifying new targets for known drugs. It can be used to overcome problems associated with traditional drug discovery by adapting existing drugs to treat new discovered diseases. Thus, it may reduce associated risk, cost and time required to identify and verify new drugs. Nowadays, drug repositioning has received more attention from industry and academia. To tackle this problem, researchers have applied many different computational methods and have used var...
Target-specific delivery of doxorubicin to human glioblastoma cell line via ssDNA aptamer
BAYRAÇ, TAHİR; Akca, Oya Ercan; Eyidogan, Fusun Inci; Öktem, Hüseyin Avni (Springer Science and Business Media LLC, 2018-03-01)
Targeted drug delivery approaches have been implementing significant therapeutic gain for cancer treatment since last decades. Aptamers are one of the mostly used and highly selective targeting agents for cancer cells. Herein, we address a nano-sized targeted drug delivery approach adorned with A-172 glioblastoma cell-line-specific single stranded DNA (ssDNA) aptamer in which the chemotherapeutic agent Doxorubicin (DOX) had been conjugated. DNA aptamer, GMT-3, was previously selected for specific recognitio...
An Extensible security infrastructure for the secondary use of electronic health records in clinical research
Eryılmaz, Elif; Toroslu, İsmail Hakkı; Doğaç, Asuman; Department of Computer Engineering (2013)
In order to facilitate clinical research studies re-using Electronic Health Records (EHR) has a great potential. Besides interoperability, safeguarding the security and privacy of the medical data in the context of secondary use for clinical research is one of the most important challenges in this respect. In order to ensure that the clinical information is shared among EHR systems and clinical research systems in an ethical and safe way, there needs to be standards-based and adaptable security and privacy ...
Weight Gain in Risperidone Therapy Investigation of Peripheral Hypothalamic Neurohormone Levels in Psychotic Patients
Yanık, Tülin; Sutcigil, Levent; Ak, Mehmet (Ovid Technologies (Wolters Kluwer Health), 2013-10-01)
The use of antipsychotic drugs has started a new era in the treatment of psychotic disorders. Nevertheless, they cause complications in the long-term treatment, which is mainly weight gain. In this study, we investigated circulating levels of hypothalamic neuropeptides, which are related to appetite regulation, neuropeptide Y (NPY), alpha-melanocyte-stimulating hormone (alpha-MSH), cocaine- and amphetamine-regulated transcript (CART), and leptin, in first-attack psychotic patients who were treated with an a...
Citation Formats
M. K. Kahveci, “Recommendation generation for performance improvement by using cross-organizational process mining,” M.S. - Master of Science, Middle East Technical University, 2015.
METU IIS - Integrated Information Service open@metu.edu.tr