Abstract Early palliative supportive care (ePSC) has been increasingly recognized as an essential component of comprehensive cancer care, with demonstrated benefits in terms of quality of life, symptom burden, psychological distress, and end-of-life care. Although its integration has been extensively investigated in patients with solid tumors, evidence regarding hematological malignancies remains more limited, and the specific components through which ePSC exerts its beneficial effects are still not fully understood. The present study aimed to explore the content of real-world outpatient ePSC consultations delivered to patients with hematological malignancies, with the goal of identifying the main domains of care addressed during clinical encounters and examining how these themes emerge across the care trajectory. This was a single-center qualitative observational study based on prospectively collected data obtained at the Centro Oncologico Modenese, AOU Policlinico di Modena. The study cohort included 55 patients with hematological malignancies, mainly acute myeloid leukemia, lymphoma, and multiple myeloma. A total of 128 outpatient ePSC consultations were audio-recorded, manually transcribed, anonymized, and analyzed using artificial intelligence and natural language processing techniques. Both unsupervised and supervised approaches were applied to identify recurrent linguistic patterns and clinically meaningful communication domains. Unsupervised analysis showed limited separation of conversation chunks according to visit number, suggesting that the content of ePSC encounters cannot be fully explained by visit chronology alone. Supervised analysis was designed to classify conversation segments according to predefined domains of care derived from the literature, including symptom management, coping, illness understanding, treatment decision-making, family involvement, and end-of-life planning. Overall, this study provides a preliminary framework for the systematic analysis of ePSC consultations in hematological malignancies. By directly examining real-life clinical encounters, it contributes to a better understanding of the core elements of ePSC and may support the future development of structured, reproducible, and patient-centered models of integrated palliative care.

Defining the Core Constituent Elements of the Early Palliative Care Intervention: A Prospective Qualitative AI Analysis of Its Delivery in Real-World Clinical Encounters

TURINA, ROSA
2025/2026

Abstract

Abstract Early palliative supportive care (ePSC) has been increasingly recognized as an essential component of comprehensive cancer care, with demonstrated benefits in terms of quality of life, symptom burden, psychological distress, and end-of-life care. Although its integration has been extensively investigated in patients with solid tumors, evidence regarding hematological malignancies remains more limited, and the specific components through which ePSC exerts its beneficial effects are still not fully understood. The present study aimed to explore the content of real-world outpatient ePSC consultations delivered to patients with hematological malignancies, with the goal of identifying the main domains of care addressed during clinical encounters and examining how these themes emerge across the care trajectory. This was a single-center qualitative observational study based on prospectively collected data obtained at the Centro Oncologico Modenese, AOU Policlinico di Modena. The study cohort included 55 patients with hematological malignancies, mainly acute myeloid leukemia, lymphoma, and multiple myeloma. A total of 128 outpatient ePSC consultations were audio-recorded, manually transcribed, anonymized, and analyzed using artificial intelligence and natural language processing techniques. Both unsupervised and supervised approaches were applied to identify recurrent linguistic patterns and clinically meaningful communication domains. Unsupervised analysis showed limited separation of conversation chunks according to visit number, suggesting that the content of ePSC encounters cannot be fully explained by visit chronology alone. Supervised analysis was designed to classify conversation segments according to predefined domains of care derived from the literature, including symptom management, coping, illness understanding, treatment decision-making, family involvement, and end-of-life planning. Overall, this study provides a preliminary framework for the systematic analysis of ePSC consultations in hematological malignancies. By directly examining real-life clinical encounters, it contributes to a better understanding of the core elements of ePSC and may support the future development of structured, reproducible, and patient-centered models of integrated palliative care.
2025
ePSC
Hematology
Content Analysis
Real-World Evidence
AI
File in questo prodotto:
File Dimensione Formato  
Turina.Rosa.pdf.pdf

accesso aperto

Dimensione 5.79 MB
Formato Adobe PDF
5.79 MB Adobe PDF Visualizza/Apri

I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14251/6818