Normal Tissue Complication Probability Modelling for Toxicity Prediction and Patient Selection in Proton Beam Therapy to the Central Nervous System: A Literature Review

Purpose The study aims to enhance the efficiency and accuracy of literature reviews on normal tissue complication probability (NTCP) in head and neck cancer patients using radiation therapy. It employs meta-analysis (MA) and natural language processing (NLP). Material and methods The study consists of two parts. First, it employs MA to assess NTCP models for xerostomia, dysphagia, and mucositis after radiation therapy, using Python 3.10.5 for statistical analysis. Second, it integrates NLP with convolutional neural networks (CNN) to optimize literature search, reducing 3256 articles to 12. CNN settings include a batch size of 50, 50–200 epoch range and a 0.001 learning rate. Results The study's CNN-NLP model achieved a notable accuracy of 0.94 after 200 epochs with Adamax optimization. MA showed an AUC of 0.67 for early-effect xerostomia and 0.74 for late-effect, indicating moderate to high predictive accuracy but with high variability across studies. Initial CNN accuracy of 66.70% improved to 94.87% post-tuning by optimizer and hyperparameters. Conclusion The study successfully merges MA and NLP, confirming high predictive accuracy for specific model-feature combinations. It introduces a time-based metric, words per minute (WPM), for efficiency and highlights the utility of MA and NLP in clinical research.

Section: Discussionmentioning

confidence: 99%

Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer

Lee,

Hsieh,

Yang

et al. 2024

“…Due to the lack of robust prediction models of photons and protons for this toxicity, it is impossible to predict the risk of hearing loss based on the patient's disease and treatment characteristics. The Normal Tissue Complication Probability (NTCP) model has been employed in previous studies to guide clinical judgment of proton beam therapy (PBT) [ 48 ]. In S. Gaito et al’s study, the risk reduction of secondary tumors with PBT was estimated to be considerable compared with conventional photon radiotherapy through modeling studies.…”

Section: Discussionmentioning

confidence: 99%

“…In S. Gaito et al’s study, the risk reduction of secondary tumors with PBT was estimated to be considerable compared with conventional photon radiotherapy through modeling studies. The clinical benefit of PBT primarily depends on the location of the tumor relative to the organ at risk and on the prescribed dose [ 48 ]. A multicenter study evaluating proton therapy and volumetric modulated arc therapy (VMAT) by establishing an NTCP model demonstrated that the reduction of NTCP in the population had a significant impact on auditory toxicity (VMAT: 8.0%; Proton: 3.3%).…”

Section: Discussionmentioning

confidence: 99%

The relevance of ototoxicity induced by radiotherapy

Huang

Zhou

An³

et al. 2023

Background The risk of ototoxicity, characterized by hearing impairment, tinnitus, or middle ear inflammation, is elevated in both child and adult cancer survivors who have undergone head-neck or brain radiation, or a combination of the two. To provide optimal care for these cancer survivors and minimize subsequent complications, it is crucial to comprehend the relationship between radiotherapy and ototoxicity. Methods A comprehensive search of databases, including the Cochrane Library, PubMed, Embase, and Web of Science, was conducted from the inception of the knowledge base up until January 2023. The metafor-package was employed to compare ototoxicity rates in individuals receiving radiotherapy. Two independent assessors extracted data and analyzed targets using a random-effects model. Results Out of the 28 randomized controlled trials (RCTs) included in the analysis, 25 were prospective RCTs. Subgroup analysis revealed that mean cochlear radiation dose, primary tumor location, radiotherapy modality, and patient age significantly influenced total hearing impairment. Intensity-modulated radiotherapy was associated with less ototoxicity than 2D conventional radiotherapy (OR, 0.53; 95% CI, 0.47–0.60; P = 0.73; I2 = 0%). Stereotactic radiotherapy appeared to be a superior option for hearing preservation compared to radiosurgery (OR, 1.44; 95% CI, 1.00–2.07; P = 0.69; I2 = 0%). Children demonstrated a higher risk of hearing impairment than adults. More than 50% of patients with vestibular neuroadenoma experienced hearing impairment following radiation therapy. A strong association was observed between the average cochlear radiation dose and hearing impairment. Increased cochlear radiation doses may result in a heightened risk of hearing impairment. Conclusion Several risk factors for radiation-induced hearing impairment were identified in this study. High cochlear radiation doses were found to exacerbate the risk of hearing impairment resulting from radiation therapy.

“…A reduction of grade 3 toxicity is clinically relevant and important in justifying the higher cost of proton therapy. In recent years, specific NTCP have been modeling for patient selection for proton therapy [ 22 , 24 ]. Schröder et al develop a NTCP model combining clinical and dosimetric factors focused on grade ≥ 2 radionecrosis in a large cohort of patients receiving proton, the best fit was found for the model containing age, prescription dose, D1cc (Gy), and hypertensive blood pressure as risk factors [ 25 ].…”

Section: Discussionmentioning

confidence: 99%

Research trends of radiation induced temporal lobe injury in patients with nasopharyngeal carcinoma from 2000 to 2022: a bibliometric analysis

Guan,

Yu,

Liu

et al. 2023

Background In patients with nasopharyngeal cancer (NPC), radiation-induced temporal lobe injury (TLI) is the most dreaded late-stage complication following radiation therapy (RT). We currently lack a definitive algorithmic administration for this entity. In the meantime, the pathogenesis of TLI and the mechanism-based interventions to prevent or treat this adverse effect remain unknown. To better answer the aforementioned questions, it is necessary to comprehend the intellectual foundations and prospective trends of this field through bibliometric analysis. Methods Articles were gathered from the Web of Science Core Collection (WoSCC) database between 2000 and 2022. CiteSpace was utilized to create a country/institutional co-authorship network, perform dual-map analysis, and find keywords with citation bursts. VOSviewer was used to build networks based on author co-authorship, journal citation, co-citation analysis of authors, references, and journals, and keyword co-occurrence. Results A total of 140 articles and reviews were included in the final analysis. The number of publications has steadily increased with some fluctuations over the years. The country and institution contributing most to this field are the China and Sun Yat-Sen University. Han Fei was the most prolific author, while Lee Awm was the most frequently cited. The analysis of co-occurrence revealed three clusters, including: “radiation-induced injury or necrosis in NPC,” “clinical studies on chemotherapy/radiotherapy complications and survival in recurrent NPC,” and “IMRT/chemotherapy outcomes and toxicities in head and neck cancer”). Most recent keyword bursts were “volume,” “temporal lobe injury,” “toxicities,” “model,” “survival,” “intensity modulated radiotherapy,” “induced brain injury,” “head and neck cancer,” and “temporal lobe.” Conclusion This study provides some insights of the major areas of interest in the field of radiation-induced TLI in patients with NPC by bibliometric analyses. This study assists scholars in locating collaborators and significant literature in this field, provides guidance for publishing journals, and identifies research hotspots. This analysis acknowledges significant contributions to the discipline and encourages the scientific community to conduct additional research.