Investigator

Massimo Criscione

Obstetrics and Gynecology Resident · Università degli Studi di Sassari Facoltà di Medicina e Chirurgia

MCMassimo Criscione
Papers(2)
Gliomatosis peritonei…Natural language proc…
Collaborators(10)
Matteo BrunoNicolò BizzarriShira SternStefano PatarnelloTal Keidar HaranAndrea RosatiAnna FagottiDavide ArrigoGiacomo GuidiLiat Matan
Institutions(3)
Agostino Gemelli Univ…Hadassah Medical Cent…Universit Cattolica D…

Papers

Gliomatosis peritonei with ovarian teratoma: an international multicenter case series

Gliomatosis peritonei (GP) is a rare condition characterized by peritoneal implants of mature glial tissue, macroscopically resembling peritoneal carcinomatosis. It is usually associated with ovarian mature or immature teratoma. To describe the clinical characteristics, treatment, and prognosis of cases with GP. Multi-center retrospective study of patients diagnosed with ovarian teratoma and GP between 2000 and 2023. Non-gynecological GP cases were excluded. Overall, 23 patients were included. Median age was 25 years (range; 10-38). Median ovarian tumor size was 19 cm (range; 6-35). The main symptom was abdominal pain (n = 13). Histology was mature teratoma in 13% (n = 3), and immature teratoma in 87% (n = 20) of cases, of which 90% (n = 18) was pure teratomas and 10% (n = 2) was mixed with yolk sac tumor. Overall, 60% were grade 3. Fertility-sparing surgery was performed in 87% (n = 20, of them 18 underwent unilateral salpingo-oophorectomy and 2 cystectomy ± further biopsies) without macroscopic residual disease in 91% (n = 21), and 78% (n = 18) were diagnosed at stage I. Adjuvant chemotherapy was given in 7 cases, only with grade 2 or more. Twelve women relapsed after a median of 43 months. However, only 2 relapses had immature teratoma components. Three patients had a second relapse after a median of 9 months. Over a median follow-up of 81 months (range; 7-270), the entire cohort remained alive and 3 live births were reported. GP is mostly associated with high-grade early-stage immature teratoma in young patients. Resection of peritoneal implants is crucial for the accurate diagnosis and optimal treatment planning. Relapses are mostly mature, therefore, offering fertility-sparing treatment in pre-menopausal cases could be considered.

Natural language processing as consultation service platform or clinical decision support system in gynecologic oncology: a systematic review.

Natural language processing is emerging as a key application of artificial intelligence in oncology. This systematic review aims to evaluate the performance and methodological frameworks of natural language processing systems in gynecologic oncology. We conducted a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis 2020 guidelines. MEDLINE, EMBASE, and Web of Science were searched for studies published between January 2015 and February 2025. Outcomes were synthesized across 3 research questions: the accuracy of natural language processing systems used as consultation service platforms; the accuracy of natural language processing systems used as clinical decision support systems; and the benchmarking methodologies applied, including their associated methodological outcomes. Consultation service platforms deliver general medical information, whereas clinical decision support systems provide recommendations that are integrated into the patient's clinical workflow. This review analyzed 12 retrospective studies. Consultation service platforms were less accurate than clinicians (60% vs 86.7%) and rated lower in response quality (2.96/5 vs 4.2/5) but outperformed guideline-based answers (1.54/2 vs 1.38/2). In cervical cancer, ChatGPT surpassed experts (7.0 vs 6.1). ChatGPT-4 showed a concordance of 70% with the National Comprehensive Cancer Network and 60% with the European Society of Gynaecological Oncology guidelines in clinical decision support tasks, with an overall recommendation accuracy of 75%. IBM Watson achieved a 72.8% concordance with guidelines. Prompting was applied from 100% to 37.5% across studies. Qualitative benchmarking varied across studies: 83.3% used clinical guidelines and 37.5% of consultation service platforms studies used expert answers. Four- or 5-point scales and binary scoring were used to assess consultation service platforms and clinical decision support systems, respectively. Clinicians remain superior in complex reasoning, but natural language processing systems demonstrate robust performance in guideline-driven tasks, with advantages in speed, readability, and reproducibility. However, performance declined in nuanced scenarios and among under-represented patient sub-groups. Large language models currently play a supportive rather than substitutive role in gynecologic oncology.

8Works
2Papers
13Collaborators

Positions

2021–

Obstetrics and Gynecology Resident

Università degli Studi di Sassari Facoltà di Medicina e Chirurgia

Education

2020

Doctor in Medicine and Surgery

University of Parma