Rotbei, Sayna (2024) Evaluating Artificial Intelligence Capabilities to Support Clinical Decisions on the Path Toward Healthcare 4.0. [Tesi di dottorato]
Anteprima |
Testo
Rotbei_Sayna_36.pdf Download (10MB) | Anteprima |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | Evaluating Artificial Intelligence Capabilities to Support Clinical Decisions on the Path Toward Healthcare 4.0 |
| Autori: | Autore Email Rotbei, Sayna sayna.rotbei@unina.it |
| Data: | 12 Aprile 2024 |
| Numero di pagine: | 166 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Ingegneria Elettrica e delle Tecnologie dell'Informazione |
| Dottorato: | Information and Communication Technology for Health |
| Ciclo di dottorato: | 36 |
| Coordinatore del Corso di dottorato: | nome email Riccio, Daniele daniele.riccio@unina.it |
| Tutor: | nome email Botta, Alessio [non definito] |
| Data: | 12 Aprile 2024 |
| Numero di pagine: | 166 |
| Parole chiave: | Artificial Intelligence, Machine Learning, Deep Learning, Healthcare 4.0 |
| Settori scientifico-disciplinari del MIUR: | Area 09 - Ingegneria industriale e dell'informazione > ING-INF/05 - Sistemi di elaborazione delle informazioni |
| Depositato il: | 15 Apr 2024 09:36 |
| Ultima modifica: | 10 Mar 2026 12:09 |
| URI: | http://www.fedoa.unina.it/id/eprint/15396 |
Abstract
Healthcare faces obstacles that hinder optimal care. Healthcare 4.0 provides real-time personalized healthcare services with state-of-the-art technologies. Artificial Intelligence (AI) is a critical technique for accurately diagnosing and predicting health issues. Even though AI has outperformed human diagnosis in several fields, its reliability remains unclear. Utilizing AI in this field requires understanding whether the technology is mature enough to support clinicians in their daily activities. In order to evaluate the potential of AI, in this thesis, four distinct areas of healthcare were studied, each presenting unique challenges and opportunities. The work started with assessing the potential of AI to support doctors to have an insight into the future life quality of prostate cancer patients after prostatectomy. Then, psychiatric diseases were investigated, widespread issues of recent years, evaluating the potential of this technology to support clinicians in understanding the impact of treatment methods or lifestyle. Another important chronic disease, specifically diabetes, was then studied to understand if AI can support physicians in predicting glycemia events. This was a collaborative work with San Carlos Clinical Hospital in Madrid. The cardiology area was finally considered to evaluate the potential of Deep Learning (DL) methods for supporting clinicians to interpret Electrocardiogram (ECG) signals and relate them to cardiovascu- lar issues. This was a joint work with Warwick University. The experiments conducted in these areas show accuracy values ranging from 63% to 95%. These results demonstrate the potential of AI in supporting clinicians toward healthcare 4.0. However, a crucial prerequisite for obtaining high accuracy is the availability of large and well-organized datasets. AI has also shown the ability to identify complex and sometimes hidden relationships among variables considered in the studies, even without a properly arranged and large dataset. It has also been able to identify the most crucial variable for gaining insights into a patient’s future.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
