Publications by authors named "Semih Utku"

Federated learning is a collaborative machine learning paradigm where multiple parties jointly train a predictive model while keeping their data. On the other hand, multi-label learning deals with classification tasks where instances may simultaneously belong to multiple classes. This study introduces the concept of Federated Multi-Label Learning (FMLL), combining these two important approaches.

View Article and Find Full Text PDF

Aim: To demonstrate a custom spine disease analytical evaluation module that can instantly, accurately, and effectively analyze the widely accepted outcome measurements.

Material And Methods: The data input and analysis processes were evaluated on a timely basis to compare the traditional paper-based manual data entry method with the spine surgery database (SSD) platform data entry method. The data of 116 patients in the cervical degenerative patient group were analyzed using the upgraded version of the SSD.

View Article and Find Full Text PDF

Drugs need to be used regularly and correctly in order to be effective. When medicines are used correctly, negativities that threaten human health and life can be avoided, but they can cause unwanted situations that can occur until the end of life when they are used incorrectly. The most common drug administration errors in hospitals are: The wrong dosage of the drug given to the patient, the timing and / or the method of administration, the wrong drug given to the patient, the drug given to the wrong patient, or even not given.

View Article and Find Full Text PDF

Patient delivery time is no longer considered as the only critical factor, in ambulatory services. Presently, five clinical performance indicators are used to decide patient satisfaction. Unfortunately, the emergency ambulance services in rapidly growing metropolitan areas do not meet current satisfaction expectations; because of human errors in the management of the objects onboard the ambulances.

View Article and Find Full Text PDF

Reliable sources report that errors in drug administration are increasing the number of harmed or killed inpatients, during healthcare. This development is in contradiction to patient safety norms. A correctly designed hospital-wide ubiquitous system, using advanced inpatient identification and matching techniques, should provide correct medicine and dosage at the right time.

View Article and Find Full Text PDF

Aim: This study presents a Turkish academic database application platform which is specialized for spinal surgery clinics. The application provides a userfriendly interface and easy access to the patients' data due to a hierarchical structure. Patient diagnosis, treatment and follow-up process data are recorded regularly and systematically.

View Article and Find Full Text PDF