ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board?

OBJECTIVE: To evaluate ChatGPT's performance in brain glioma adjuvant therapy decision-making. METHODS: We randomly selected 10 patients with brain gliomas discussed at our institution's central nervous system tumour board (CNS TB). Patients' clinical status, surgical outcome, textual imaging information and immuno-pathology results were provided to ChatGPT V.3.5 and seven CNS tumour experts. The chatbot was asked to give the adjuvant treatment choice, and the regimen while considering the patient's functional status. The experts rated the artificial intelligence-based recommendations from 0 (complete disagreement) to 10 (complete agreement). An intraclass correlation coefficient agreement (ICC) was used to measure the inter-rater agreement. RESULTS: Eight patients (80%) met the criteria for glioblastoma and two (20%) were low-grade gliomas. The experts rated the quality of ChatGPT recommendations as poor for diagnosis (median 3, IQR 1-7.8, ICC 0.9, 95% CI 0.7 to 1.0), good for treatment recommendation (7, IQR 6-8, ICC 0.8, 95% CI 0.4 to 0.9), good for therapy regimen (7, IQR 4-8, ICC 0.8, 95% CI 0.5 to 0.9), moderate for functional status consideration (6, IQR 1-7, ICC 0.7, 95% CI 0.3 to 0.9) and moderate for overall agreement with the recommendations (5, IQR 3-7, ICC 0.7, 95% CI 0.3 to 0.9). No differences were observed between the glioblastomas and low-grade glioma ratings. CONCLUSIONS: ChatGPT performed poorly in classifying glioma types but was good for adjuvant treatment recommendations as evaluated by CNS TB experts. Even though the ChatGPT lacks the precision to replace expert opinion, it may serve as a promising supplemental tool within a human-in-the-loop approach.

Outcomes of adolescents and young adults treated for brain and skull base tumors with pencil beam scanning proton therapy.

BACKGROUND: The use of proton therapy (PT) in adolescents and young adults (AYAs) is becoming increasingly popular. This study aims to assess the outcomes and late toxicity consequences in AYAs (15-39 years) with brain/skull base tumors treated with pencil beam scanning proton therapy. METHODS: One hundred seventy six AYAs treated curatively at the Paul Scherrer Institute (PSI) were identified. Median age was 30 years (range 15-39) and median prescribed dose was 70.0 Gy (relative biological effectiveness [RBE]) (range 50.4-76.0). The most common tumors treated were chordomas/chondrosarcomas (61.4%), followed by gliomas (15.3%), and meningiomas (14.2%). RESULTS: After a median follow up of 66 months (range 12-236), 24 (13.6%) local only failures and one (0.6%) central nervous system (CNS) distant only failure were observed. The 6-year local control, distant progression-free survival, and overall survival were 83.2%, 97.4%, and 90.2%, respectively. The 6-year high-grade (≥grade [G] 3) PT-related late toxicity-free survival was 88.5%. Crude late toxicity rates were 26.2% G1, 37.8% G2, 12.2% G3, 0.6% G4, and 0.6% G5. The one G4 toxicity was a retinopathy and one G5 toxicity was a brainstem hemorrhage. The 6-year cumulative incidences for any late PT-related pituitary, ototoxicity, and neurotoxicity were 36.3%, 18.3%, and 25.6%; whilst high-grade (≥G3) ototoxicity and neurotoxicity were 3.4% and 2.9%, respectively. No secondary malignancies were observed. The rate of unemployment was 9.5% pre-PT, increasing to 23.8% post-PT. Sixty-two percent of survivors were working whilst 12.7% were in education post-PT. CONCLUSIONS: PT is an effective treatment for brain/skull base tumors in the AYA population with a reasonable late toxicity profile. Despite good clinical outcomes, around one in four AYA survivors are unemployed after treatment.

Clinical outcomes and quality of life in children and adolescents with primary brain tumors treated with pencil beam scanning proton therapy.

BACKGROUND: Long-term treatment-related toxicity may substantially impact well-being, quality of life (QoL), and health of children/adolescents with brain tumors (CBTs). Strategies to reduce toxicity include pencil beam scanning (PBS) proton therapy (PT). This study aims to report clinical outcomes and QoL in PBS-treated CBTs. PROCEDURE: We retrospectively reviewed 221 PBS-treated CBTs aged <18 years. Overall-free (OS), disease-free (DFS), and late-toxicity-free survivals (TFS), local control (LC) and distant (DC) brain/spinal control were calculated using Kaplan-Meier estimates. Prospective QoL reports from 206 patients (proxies only ≤4 years old [yo], proxies and patients ≥5 yo) were descriptively analyzed. Median follow-up was 51 months (range, 4-222). RESULTS: Median age at diagnosis was 3.1 years (range, 0.3-17.7). The main histologies were ependymoma (n = 88; 39.8%), glioma (n = 37; 16.7%), craniopharyngioma (n = 22; 10.0%), atypical teratoid/rhabdoid tumor (ATRT) (n = 21; 9.5%) and medulloblastoma (n = 15; 6.8%). One hundred sixty (72.4%) patients received chemotherapy. Median PT dose was 54 Gy(relative biological effectiveness) (range, 18.0-64.8). The 5-year OS, DFS, LC, and DC (95% CI) were 79.9% (74-85.8), 65.2% (59.8-70.6), 72.1% (65.4-78.8), and 81.8% (76.3-87.3), respectively. Late PT-related ≥G3 toxicity occurred in 19 (8.6%) patients. The 5-year ≥G3 TFS was 91.0% (86.3-95.7). Three (1.4%) secondary malignancies were observed. Patients aged ≤3 years at PT (P = .044) or receiving chemotherapy (P = .043) experienced more ≥G3 toxicity. ATRT histology independently predicted distant brain failure (P = .046) and death (P = .01). Patients aged ≥5 years self-rated QoL higher than their parents (proxy assessment). Both reported lower social functioning and cognition after PT than at baseline, but near-normal long-term global well-being. QoL was well below normal before and after PT in children ≤4 years. CONCLUSIONS: The outcome of CBTs was excellent after PBS. Few patients had late ≥G3 toxicity. Patients aged <5 years showed worse QoL and toxicity outcomes.

Early results and volumetric analysis after spot-scanning proton therapy with concomitant hyperthermia in large inoperable sacral chordomas.

OBJECTIVE: Large inoperable sacral chordomas show unsatisfactory local control rates even when treated with high dose proton therapy (PT). The aim of this study is assessing feasibility and reporting early results of patients treated with PT and concomitant hyperthermia (HT). METHODS:: Patients had histologically proven unresectable sacral chordomas and received 70 Gy (relative biological effectiveness) in 2.5 Gy fractions with concomitant weekly HT. Toxicity was assessed according to CTCAE_v4. A volumetric tumor response analysis was performed. RESULTS:: Five patients were treated with the combined approach. Median baseline tumor volume was 735 cc (range, 369-1142). All patients completed PT and received a median of 5 HT sessions (range, 2-6). Median follow-up was 18 months (range, 9-26). The volumetric analysis showed an objective response of all tumors (median shrinkage 46%; range, 9-72). All patients experienced acute Grade 2-3 local pain. One patient presented with a late Grade 3 iliac fracture. CONCLUSION: Combining PT and HT in large inoperable sacral chordomas is feasible and causes acceptable toxicity. Volumetric analysis shows promising early results, warranting confirmation in the framework of a prospective trial. ADVANCES IN KNOWLEDGE:: This is an encouraging first report of the feasibility and early results of concomitant HT and PT in treating inoperable sacral chordoma.

Proton therapy for brain tumours in the area of evidence-based medicine.

ADVANCES IN KNOWLEDGE: This review details the indication of brain tumors for proton therapy and give a list of the open prospective trials for these challenging tumors.

Oligorecurrent Nodal Prostate Cancer: Long-term Results of an Elective Nodal Irradiation Approach.

OBJECTIVES: The objective of this study was to report long-term results of elective nodal radiotherapy (ENRT) in prostate cancer (PCa) patients with oligorecurrent nodal disease after primary treatment. METHODS: Data of 53 oligorecurrent PCa patients (N1 and/or M1a) with ≤5 nodal metastases (n=108) treated with ENRT combined with androgen deprivation therapy (ADT) between 2004 and 2016 were retrospectively reviewed. Median prostate-specific antigen (PSA) and PSA doubling time (DT) were 3.4 ng/mL and 5 months, respectively. At restaging, 45% of the patients presented single nodal metastases, mainly located in the pelvis (n=38). All patients underwent ENRT between 45 and 50.4 Gy with a boost on positive nodes (median 64.4 Gy; 54 to 69 Gy) using mainly VMAT (n=24) or IMRT (n=21) techniques. Concomitant ADT was administered to all patients for a median time of 6 months. RESULTS: After a median follow-up after ENRT of 44 months (range, 2 to 133), the 5-year biochemical disease-free and distant progression-free survival (DPFS) rates were 43% and 58%, respectively, with worse DPFS observed in patients with a PSA-doubling time <3 months (36.8% vs. 63.6%; P=0.029). Seventeen of 19 clinically relapsing patients presented lesions out of the ENRT field, and 10 were again oligometastatic. Only 2 patients presented with a CTCAE v3.0 grade ≥2 genitourinary toxicity. CONCLUSIONS: ENRT combined with short-course ADT is a safe and effective salvage modality for patients with oligorecurrent nodal PCa. Prospective randomized studies comparing focal SBRT versus ENRT are warranted to define the best treatment strategy.

68Ga-PSMA PET/MR-Positive Peritoneal Metastasis in the Falciform Ligament in Recurrent Prostate Cancer.

Synchronous or metachronous metastases develop in approximately one third of all prostate cancer (PCa) patients. Main sites of metastasis include lymph nodes, bone, lung and liver. Secondary peritoneal carcinomatosis is very rare in PCa, with only a few published cases. Ga-PSMA PET-based imaging is a promising tool for staging and restaging PCa. We report a case of Ga-PSMA PET/MR-positive peritoneal metastasis as site of primary relapse after definitive PCa treatment in a 58-year-old man with a prostate-specific antigen of 30 ng/mL at time of the study. Exploratory laparoscopy and subsequent histopathologic examination confirmed nonascitic peritoneal PCa carcinomatosis.