SIMPLIFication of Care Pathways for Patients With Rare Brain Tumors Through Artificial Intelligence

Official title

SIMPLIF-AI: SIMPLIFication and Standardization of Care Pathways for Patients With Rare Brain Tumors Through Artificial Intelligence

Overview

This study focuses on rare brain tumors, which are heterogeneous entities with different morphological, biological, and clinical characteristics. Due to their rarity, many of these tumors fall under the RARECARE definition of rare tumors. The main objective of the study is to standardize care models and pathways for patients with rare brain tumors, using Artificial Intelligence (AI) and Machine Learning (ML) techniques to identify specific predictors of postoperative outcomes. The study includes both retrospective and prospective phases, with the collection of clinical, cognitive, and psychological data at various time points. Patients will undergo an early neuro-cognitive rehabilitation program using the RehaCom software, which will be conducted at home. The goal is to improve the quality of life and care for patients through a multidisciplinary and innovative approach.

Detailed description

Participants will be adults with rare brain tumors and will be enrolled at two neurosurgery centers in Italy. The study aims to create a network of professionals specialized in predicting surgical outcomes, thereby improving the overall quality of care and the quality of life for patients.

This study aims to improve the care and outcomes for patients with rare brain tumors (rBT) by standardizing clinical pathways and utilizing advanced technologies such as Artificial Intelligence (AI) and Machine Learning (ML). Rare brain tumors, including astrocytomas, oligodendrogliomas, neuronal tumors, malignant meningiomas, and embryonal tumors, are defined as rare due to their low incidence (\<6 cases per 100,000 people/year).

The study will be conducted in two phases: a retrospective phase and a prospective phase. The retrospective phase will involve the use of existing neurosurgical databases to implement ML algorithms. The prospective phase will include the collection of clinical, cognitive, and psychological data at multiple time points (pre-surgery, discharge, 3 months post-surgery, and 12 months post-surgery).

Patients will participate in an early neuro-cognitive rehabilitation program using the RehaCom software, designed to enhance cognitive functions potentially affected by surgery. The rehabilitation will be conducted at the patient's home.

The primary objective is to develop a common evaluation protocol that includes clinical, cognitive, psychological, and sociodemographic measures. Secondary objectives include identifying predictors of surgical outcomes through retrospective and prospective studies and developing predictive models for rare brain tumors.

The study will enroll approximately 200 adult patients from two neurosurgery centers in Italy. Inclusion criteria include adults (≥18 years) undergoing craniotomy for rare brain tumors, while exclusion criteria include patients undergoing stereotactic biopsy, those with psychiatric disorders, or those lacking the necessary technology for home-based rehabilitation.

The ultimate goal is to create a multidisciplinary network of professionals specialized in predicting surgical outcomes, thereby improving the overall quality of care and the quality of life for patients with rare brain tumors.

Interventions

• Device RehaCom
  Participants will receive a personalized neuro-cognitive rehabilitation program using the RehaCom software. Sessions will last approximately 30/40 minutes and will be held twice a week for 8 weeks. The rehabilitation will be aimed at enhancing and/or recovering cognitive functions that may have been compromised by the neurosurgical intervention.

Primary outcome measures

• Symptoms/Signs Onset [Time frame: Pre-operative]
• Karnofsky Performance Status (KPS) [Time frame: 12 months.]
• Neurology Assessment in Neuro-Oncology (NANO) [Time frame: From hospital admission until discharge]
• Modified Rankin Scale (mRS) [Time frame: 12 months]
• American Society of Anesthesiologists (ASA) [Time frame: Pre-operative]
• Charlson Comorbidity Index (CCI) [Time frame: Pre-operative]
• Magnetic Resonance Imaging (MRI) [Time frame: 12 months.]
• Eloquent Area Involvement [Time frame: Intra-operative]
• Cranial Nerve Manipulation [Time frame: Intra-operative]
• Vascular Manipulation [Time frame: Intra-operative]

Eligibility criteria

Inclusion criteria

• Adults (age ≥18 years)
• Both sexes
• Patients with rare brain tumors (incidence <6 cases per 100,000 people/year)
• Candidates for craniotomy for rare brain tumors
• Native Italian speakers for cognitive and psychological evaluation and neuro-cognitive rehabilitation

Exclusion criteria

• Patients undergoing stereotactic/frameless biopsy
• Patients with psychiatric disorders or on psychotropic medications
• Patients with known cognitive decline (not due to the lesion)
• Patients admitted on the same day as the surgery
• Patients with severe impairments referred to rehabilitation centers
• Patients without a Windows PC or laptop with Internet connection for neuro-cognitive rehabilitation

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

N/A

Model

Single group

Masking

Open label

Primary purpose

Treatment

Study locations

Italy · 2 centers

• Fondazione IRCCS Istituto Neurologico Carlo Besta — Milan
• ASL 1 Abruzzo Avezzano-Sulmona-L'Aquila — L’Aquila

Publications

• Fan FL, Xiong J, Li M, Wang G. On Interpretability of Artificial Neural Networks: A Survey. IEEE Trans Radiat Plasma Med Sci. 2021 Nov;5(6):741-760. doi: 10.1109/trpms.2021.3066428. Epub 2021 Mar 17. PMID 35573928
• Sagberg LM, Drewes C, Jakola AS, Solheim O. Accuracy of operating neurosurgeons' prediction of functional levels after intracranial tumor surgery. J Neurosurg. 2017 Apr;126(4):1173-1180. doi: 10.3171/2016.3.JNS152927. Epub 2016 Jun 17. PMID 27315026
• Lopez-Nunez O, Alaggio R, John I, Ciolfi A, Pedace L, Mastronuzzi A, Gianno F, Giangaspero F, Rossi S, Donofrio V, Cinalli G, Surrey LF, Tartaglia M, Locatelli F, Miele E. Melanotic Neuroectodermal Tumor of Infancy (MNTI) and Pineal Anlage Tumor (PAT) Harbor A Medulloblastoma Signature by DNA Methylation Profiling. Cancers (Basel). 2021 Feb 9;13(4):706. doi: 10.3390/cancers13040706. PMID 33572349
• Bunevicius A, Tamasauskas S, Deltuva V, Tamasauskas A, Radziunas A, Bunevicius R. Predictors of health-related quality of life in neurosurgical brain tumor patients: focus on patient-centered perspective. Acta Neurochir (Wien). 2014 Feb;156(2):367-74. doi: 10.1007/s00701-013-1930-7. Epub 2013 Nov 20. PMID 24254135
• Rolston JD, Han SJ, Lau CY, Berger MS, Parsa AT. Frequency and predictors of complications in neurological surgery: national trends from 2006 to 2011. J Neurosurg. 2014 Mar;120(3):736-45. doi: 10.3171/2013.10.JNS122419. Epub 2013 Nov 22. PMID 24266542
• Broggi M, Zattra C, Ferroli P. How to compare outcomes and complications in neurosurgery: We must make the mission possible! Surg Neurol Int. 2018 Mar 19;9:65. doi: 10.4103/sni.sni_424_17. eCollection 2018. No abstract available. PMID 29629232
• Ferroli P, Broggi M, Schiavolin S, Acerbi F, Bettamio V, Caldiroli D, Cusin A, La Corte E, Leonardi M, Raggi A, Schiariti M, Visintini S, Franzini A, Broggi G. Predicting functional impairment in brain tumor surgery: the Big Five and the Milan Complexity Scale. Neurosurg Focus. 2015 Dec;39(6):E14. doi: 10.3171/2015.9.FOCUS15339. PMID 26621412
• Senders JT, Staples PC, Karhade AV, Zaki MM, Gormley WB, Broekman MLD, Smith TR, Arnaout O. Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review. World Neurosurg. 2018 Jan;109:476-486.e1. doi: 10.1016/j.wneu.2017.09.149. Epub 2017 Oct 3. PMID 28986230

Identifiers

NCT: NCT06878469 · SIMPLIF-AI · PNRR-TR1-2023-12378146

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗