Cancer Treatment Monitoring Research Articles

3D Segmentation and Visualization of Skin Vasculature Using Line-Field Confocal Optical Coherence Tomography

This study explores the advanced imaging of skin vasculature using Line-Field Confocal Optical Coherence Tomography (LC-OCT), which offers high-resolution, three-dimensional (3D) visualization of vascular structures, especially within skin tumors. The research aims to improve the understanding of tumor angiogenesis and the complex vascular morphology associated with malignancies. The methodology involves converting original image stacks into negative images, manually tracing vessels using the Simple Neurite Tracer (SNT) plugin, and creating smoothed binary masks to reconstruct 3D models. The study’s results highlight the ability to visualize serpiginous, corkscrew-like, and irregular vessels across various skin cancers, including melanoma, squamous cell carcinoma, and basal cell carcinoma. These visualizations provide insights into vessel morphology, spatial arrangements, and blood flow patterns, which are crucial for assessing tumor growth and potential therapeutic responses. The findings indicate that 3D reconstructions from LC-OCT can uncover vascular details previously undetectable by two-dimensional imaging techniques, making it a valuable tool in dermatology for both clinical diagnostics and research. This method allows for better monitoring of skin cancer treatment and understanding of the role of vascular polymorphism in tumor development.

MXene Nanoconfinement of SAM-Modified Molecularly Imprinted Electrochemical Biosensor for Point-of-Care Monitoring of Carcinoembryonic Antigen.

The high rate of cancer worldwide and the heavy costs imposed on governments and humanity have always motivated researchers to develop point-of-care (POC) biosensors for easy diagnosis and monitoring of cancer treatment. Herein, we report on a label-free impedimetric biosensor based on Ti3C2Tx MXene and imprinted ortho-phenylenediamine (o-PD) for the detection of carcinoembryonic antigen (CEA), a biomarker for various cancers surveillance, especially colorectal cancer (CRC). Accordingly, MXene was drop-casted on the surface of a disposable silver electrode to increase the sensitivity and create high-energy nanoareas on the surface, which are usable for protein immobilization and detection. A self-assembled monolayer (SAM) was exploited for oriented CEA immobilization on the MXene-modified electrode. The monomer-protein interaction and successful protein removal were confirmed by molecular docking and atomic force microscopy (AFM) investigations to evaluate the quality of the fabricated molecularly imprinted polymer (MIP). Also, the role of MXene in increasing the electrical field inside the nanoareas was simulated using COMSOL Multiphysics software. A suitable limit of detection (9.41 ng/mL), an appropriate linear range of detection (10 to 100 ng/mL) in human serum, and a short detection time (10 min) resulted from the use of SAM/MIP next to MXene. This biosensor presented outstanding repeatability (97.60%) and reproducibility (98.61%). Moreover, acceptable accuracy (between 93.04 and 116.04%) in clinical serum samples was obtained compared with immunoassay results, indicating the high potential of our biosensor for real sample analysis. This biomimetic and disposable sensor provides a cost-effective method for facile and POC monitoring of cancer patients during treatment.

MicroRNA-Based Liquid Biopsy for Cervical Cancer Diagnostics and Treatment Monitoring.

Despite prevention strategies, cervical cancer remains a significant public health issue. Human papillomavirus plays a critical role in its development, and early detection is vital to improve patient outcomes. The incidence of cervical cancer is projected to rise, necessitating better diagnostic tools. Traditional screening methods like the cytological examination and human papillomavirus testing have limitations in sensitivity and reproducibility. Liquid-based cytology offers some improvements, but the need for more reliable and sensitive techniques persists, particularly for detecting precancerous lesions. Liquid biopsy is a non-invasive method that analyzes cancer-derived products in biofluids like blood, offering potential for real-time monitoring of tumor progression, metastasis, and treatment response. It can be based on detection of circulating tumor cells (CTCs), circulating free DNA (cfDNA), and microRNAs (miRNAs). This review particularly underlines the potential of microRNAs, which are transported by extracellular vesicles. Overall, this article underscores the importance of continued research into non-invasive diagnostic methods like liquid biopsy to enhance cervical cancer screening and treatment monitoring.

Synthetic mismatches enable specific CRISPR-Cas12a-based detection of genome-wide SNVs tracked by ARTEMIS.

Detection of pathogenic DNA variants is vital in cancer diagnostics and treatment monitoring. While CRISPR-based diagnostics (CRISPRdx) offer promising avenues for cost-effective, rapid, and point-of-care testing, achieving single-nucleotide detection fidelity remains challenging. We present an in silico pipeline that scans the human genome for targeting pathogenic mutations in the seed region (ARTEMIS), the most stringent crRNA domain. ARTEMIS identified 12% of pathogenic SNVs as Cas12a recognizable, including 928 cancer-associated variants such as BRAFV600E, BRCA2E1953∗, TP53V272M, and ALDH2E504K. Cas12a exhibited remarkable tolerance to single mismatches within the seed region. Introducing deliberate synthetic mismatches within the seed region yielded on-target activity with single-nucleotide fidelity. Both positioning and nucleobase types of mismatches influenced detection accuracy. With improved specificity, Cas12a could accurately detect and semi-quantify BRAFV600E in cfDNA from cell lines and patient liquid biopsies. These results provide insights toward rationalized crRNA design for high-fidelity CRISPRdx, supporting personalized and cost-efficient healthcare solutions in oncologic diagnostics.

PATH-10. UTILIZATION OF TUMOR-DERIVED EXTRACELLULAR VESICLES FOR PATIENT STRATIFICATION AND BIOMARKER DISCOVERY

Abstract Liquid biopsy is poised to play an increasingly important role in clinical decision making by enabling earlier cancer detection, diagnosis, patient stratification, and treatment monitoring. Most approaches rely on detection of cell-free circulating tumor DNA or circulating tumor cells in the peripheral blood of cancer patients. However, there are several limitations to these approaches, including miniscule abundance, unfavorable signal to noise ratios, and limited insight into mechanisms driving disease. Extracellular vesicles (EVs) are an alternative liquid biopsy analyte comprising lipid membrane encapsulated particles carrying diverse protein, nucleic acid, and metabolite cargos. Blood plasma of cancer patients contains EVs derived directly from tumor tissue that serve as rich sources of insight into tumor biology and disease pathology. We have developed a clinically applicable, multi-omic EV subpopulation interrogation pipeline that robustly profiles tumor-derived EVs in biofluids. We have demonstrated the ability of the platform to enrich cancer markers and detect activation of pathways driving oncogenesis across several different cancers, including brain cancer. There is a particularly compelling need for liquid biopsy-based solutions in neuro-oncology. We have applied our EV-omic (EVO) pipeline in combination with machine learning to distinguish adult high-grade gliomas from benign brain tumor and healthy patients, using blood-based EV proteomic and transcriptomic signatures. Marker profiles found to be most important for patient stratification combine markers known to be relevant in tumor tissue along with novel features. Furthermore, IDH status and MGMT methylation metadata derived from matched patient tissue for select cases was used to generate unique blood-based profiles for glioma subtypes. Lastly, we show preliminary longitudinal data demonstrating the utility of EVs to track tumor changes post-surgical resection and post-treatment. This work demonstrates that EV-omics can add significant value in the neuro-oncology space.

Comparing DCE-MRI and DSA: Understanding the embolization of hypervascular spinal metastases.

This study aims to examine and compare the effectiveness of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and Digital Subtraction Angiography (DSA) in evaluating hypervascular spinal metastases. A comprehensive literature review was conducted, utilizing top-tier databases such as PubMed, Scopus and Google Scholar, to compile an authoritative and up-to-date overview of the current advancements in the field. We synthesized key studies focusing on the advantages, limitations and efficacy of both imaging techniques. DCE-MRI provides a non-invasive method for evaluating tissue morphology, perfusion and vascularity, offering valuable information for cancer diagnosis and treatment monitoring. In contrast, DSA is an invasive procedure primarily used for embolization and diagnosing cerebrovascular events. Both modalities have distinct features regarding image acquisition, contrast agents, resolution and accessibility. DCE-MRI shows promise for cancer-related applications, offering advantages over conventional MRI by incorporating anatomical and hemodynamic parameters. While DSA remains important for cases requiring critical vascular information, further research is necessary to explore its potential therapeutic benefits in assessing vessel patency. Continued investigations are crucial to uncover additional insights and therapeutic applications for both DCE-MRI and DSA in medical imaging.

Integrating All-rounder TiO2 Accelerated Electrochemiluminescence with Dual-Quenching PDA@COF Probes for Sensitive Quantification and Protein Profiling of Tumorous Exosomes.

Exosomes have been perceived as promising biomarkers for noninvasive cancer diagnosis and treatment monitoring. However, the sensitive and accurate quantification and phenotyping of exosomes remains challenging. Herein, a versatile electrochemiluminescence (ECL) aptasensor was proposed for the sensitive analysis of tumorous exosomes. Specifically, a ternary nanohybrid (Ru-HAuTiO2), by covalently linking ECL luminophore Ru(dcbpy)32+ with gold nanoparticles (AuNPs)-decorated hollow urchin-like TiO2 (HTiO2), was ingeniously designed as a highly luminescent and self-enhanced ECL nanoemitter. Notably, the porous HTiO2 played an "all-rounder" role, including the carrier for ECL luminophores and AuNPs, coreaction accelerator, and specific exosome capturing scaffold through Ti-phosphate coordination interaction. On the other hand, a polydopamine modified covalent organic framework (PDA@COF) was employed as a quencher to remarkably attenuate the ECL of Ru-HAuTiO2 through a dual-quenching mechanism, and further labeled with a specific aptamer (Apt) of exosomal surface protein. Based on forming a Ru-HAuTiO2/exosome/Apt-PDA@COF sandwich structure on the electrode, a "signal on-off" ECL platform for tumorous exosomes was constructed, realizing sensitive detection within the range of 3.1 × 103 particles/mL to 1 × 108 particles/mL and a low limit of detection of 1.41 × 103 particles/mL, achieving phenotypic profiling of surface proteins on different tumorous exosomes. This work provides a promising alternative method for the detection and analysis of exosomes.

Microwell-assembled aluminum substrates for enhanced single-cell analysis: A novel approach for cancer cell profiling by Raman spectroscopy

Single-cell analysis is critical for advancing personalized medicine, as it reveals cell population heterogeneity that influences disease outcomes. We present a microwell-assembled aluminum substrate platform that enhances single-cell Raman spectroscopy in liquid suspension by isolating individual cells and preventing stacking and movement, which significantly improves signal stability and the signal-to-noise ratio (SNR).We applied this novel platform to analyze PC-9 lung cancer cells and BEAS-2B normal bronchial epithelial cells, identifying distinct biochemical differences. Notably, cancer cells showed higher levels of adenine, cytochromes, DNA/RNA, and unsaturated lipids, along with an increased unsaturation ratio and protein content. These findings were further validated using machine learning models. An eXtreme Gradient Boosting (XGBoost) model achieved perfect classification accuracy of 100 %, underscoring the robustness of the spectral features identified by our platform.Our platform not only enhances single-cell Raman signal detection but also holds promise for biomedical applications, including early cancer detection, treatment monitoring, and drug development. The high-throughput capacity of this platform featuring over 120,000 wells, along with its compatibility with techniques such as Raman-activated cell sorting (RACS) further extends its potential for clinical diagnostics and personalized medicine.

Electrochemical sensor for vascular endothelial growth factor based on self-assembling DNA aptamer structure

Developing vascular endothelial growth factor (VEGF) protein is essential for early cancer diagnosis and cancer treatment monitoring. This study presents the design and characterisation of an electrochemical sensor utilising a self-assembling DNA aptamer structure for the sensitive and selective detection of VEGF. The aptamer structure comprises three different parts of single-stranded DNA that are assembled prior to integration into the sensor. Polypyrrole (Ppy)-based layers were deposited onto screen-printed carbon electrodes (SPCEs) using an electrochemical deposition technique, followed by the entrapment of a self-assembled DNA aptamer structure within electrochemically formed Ppy matrix ((DNA aptamer)/Ppy). The response to the sensor toward VEGF was measured by the pulsed amperometric detection (PAD), highlighting the enhanced performance of DNA aptamer/Ppy configuration compared to bare Ppy. The sensor exhibited high sensitivity, achieving a limit of detection (LOD) of 0.21 nM for VEGF. The interaction behaviour between VEGF in the solution and the immobilise DNA aptamer/Ppy-based structure was analysed using Langmuir isotherm model. The developed electrochemical biosensor is promising for in vitro applications in early cancer diagnostics and treatment monitoring, enabling rapid screening of patient samples.

Cancer treatment monitoring using cell-free DNA fragmentomes.

Circulating cell-free DNA (cfDNA) assays for monitoring individuals with cancer typically rely on prior identification of tumor-specific mutations. Here, we develop a tumor-independent and mutation-independent approach (DELFI-tumor fraction, DELFI-TF) using low-coverage whole genome sequencing to determine the cfDNA tumor fraction and validate the method in two independent cohorts of patients with colorectal or lung cancer. DELFI-TF scores strongly correlate with circulating tumor DNA levels (ctDNA) (r = 0.90,p < 0.0001, Pearson correlation) even in cases where mutations are undetectable. DELFI-TF scores prior to therapy initiation are associated with clinical response and are independent predictors of overall survival (HR = 9.84, 95% CI = 1.72-56.10,p < 0.0001). Patients with lower DELFI-TF scores during treatment have longer overall survival (62.8 vs 29.1 months, HR = 3.12, 95% CI 1.62-6.00,p < 0.001) and the approach predicts clinical outcomes more accurately than imaging. These results demonstrate the potential of using cfDNA fragmentomes to estimate tumor burden in cfDNA for treatment response monitoring and clinical outcome prediction.

MBene Nanosheets with DNA Adsorbability for Circulating Tumor DNA Assay via Fluorescence Biosensing and Paper‐Based Microfluidic POCT

AbstractThe detection of circulating tumor DNA (ctDNA) in blood is significant for non‐invasive cancer diagnosis and treatment monitoring. Herein, MBene nanosheets is synthesized and compared with MXene via Density Functional Theory (DFT) calculations and fluorescence kinetic evaluations, for first time, revealing MBene's exceptional DNA adsorbability and discrimination to single‐stranded DNA (ssDNA) and double‐stranded DNA (dsDNA). Then, a sensitive fluorescence biosensor for ctDNA detection is developed, demonstrating impressive performance. To facilitate point‐of‐care testing (POCT) ctDNA, a paper‐based microfluidic chip incorporated a delay area and a mixing channel is designed. The constricted‐expanded structure channel optimization is guided by numerical simulations and experiments. A WeChat mini program named “ctDNA Detection” is designed for readout assay. Furthermore, cell and mice serum samples are analyzed, with Magnetic Bead@Graphene Oxide (MB@GO) and clutch probes for magnetic pre‐enrichment. The results accuracy is confirmed by its consistency with standard qPCR results (AUC = 1). The successful detection of ctDNA in post‐surgery mouse models underscored the biosensor's potential for cancer treatment monitoring. Thus, this research not only advanced the understanding of the MBene‐DNA interaction in biosensing, but also can pave the way for novel applications in bioimaging and nanopore‐based nucleic acid sequencing, leveraging the digital transformation of DNA base‐MBene adsorption differences.

Near‐Infrared Spectroscopy and Aquaphotomics in Cancer Research: A Pilot Study

ABSTRACTCurrently, the majority of methods to monitor cancer treatment through the analysis of body fluids are based on a highly selective detection of single molecules or cells. In this study, we are considering the analysis of the aqueous medium of liquid samples, that is, water, itself, using aquaphotomics and near‐infrared spectroscopy (NIR) for spectral data acquisition and processing, within cancer research. Water, as a molecular system, is a rich source of information about the current state of a patient, which can be extracted from near‐infrared spectra of liquid samples via simple algorithms based on multivariate data analysis. The reported results, obtained ex vivo of body fluids, demonstrate the potential of aquaphotomics in cancer research.

A development of sensor based on ZnO@ZIF-8 for detection of 5-Fluorouracil as a liver cancer medicine in serum samples

In this work, a new electrochemical sensor for the detection of 5-Fluorouracil (5-FU) as a liver cancer medicine in serum samples is developed and evaluated. Green synthesized Zinc Oxide (ZnO) nanorods and a modified glassy carbon electrode (ZnO@ZIF-8/GCE) are used in the sensor, which shows encouraging findings in terms of selectivity, stability, and sensitivity. High sensitivity and selectivity towards 5-FU are demonstrated by the ZnO@ZIF-8 nanocomposite electrode, even in presence of a variety of potential electroactive interferences. The ZnO@ZIF-8/GCE’s stability and repeatability in identifying 5-FU were examined using Differential Pulse Voltammetry (DPV) analysis. The low detection limit (DL) of the sensor system was found to be 0.022 µM. The DL is defined as the change in peak current by three relative standard deviations. The range of the linear determination is 2 µM–660 µM. The ZnO@ZIF-8/GCE’s applicability in identifying 5-FU was assessed by determining 5-FU in human-serum specimens using DPV and the manufactured sensor. The Relative Standard Deviation (RSD) values varied between 3.85 % and 4.42 %, while the recoveries ranged from 98.20 % to 99.44 %. In the context of monitoring cancer treatment, this research constitutes a major advancement in the field of electrochemical sensing.

Prospects and Current Challenges of Extracellular Vesicle-Based Biomarkers in Cancer.

Cancer continues to impose a substantial global health burden, particularly among the elderly, where the ongoing global demographic shift towards an ageing population underscores the growing need for early cancer detection. This is essential for enabling personalised cancer care and optimised treatment throughout the disease course to effectively mitigate the increasing societal impact of cancer. Liquid biopsy has emerged as a promising strategy for cancer diagnosis and treatment monitoring, offering a minimally invasive method for the isolation and molecular profiling of circulating tumour-derived components. The expansion of the liquid biopsy approach to include the detection of tumour-derived extracellular vesicles (tdEVs) holds significant therapeutic opportunity. Evidence suggests that tdEVs carry cargo reflecting the contents of their cell-of-origin and are abundant within the blood, exhibiting superior stability compared to non-encapsulated tumour-derived material, such as circulating tumour nucleic acids and proteins. However, despite theoretical promise, several obstacles hinder the translation of extracellular vesicle-based cancer biomarkers into clinical practice. This critical review assesses the current prospects and challenges facing the adoption of tdEV biomarkers in clinical practice, offering insights into future directions and proposing strategies to overcome translational barriers. By addressing these issues, EV-based liquid biopsy approaches could revolutionise cancer diagnostics and management.

65O Cancer treatment monitoring using cell-free DNA fragmentomes

65O Cancer treatment monitoring using cell-free DNA fragmentomes

Single Methylation Sensitive Restriction Endonuclease-Based Cascade Exponential Amplification Assay for Visual Detection of DNA Methylation at Single-Molecule Level.

Function as a potential cancer biomarker, DNA methylation shows great significance in cancer diagnosis, prognosis, and treatment monitoring. While the lack of an ultrasensitive, specific, and accurate method at the single-molecule level hinders the analysis of the exceedingly low levels of DNA methylation. Herein, based on the outstanding recognition and digestion ability of methylation-sensitive restriction endonuclease (MSRE), we established a single MSRE-based cascade exponential amplification method, which requires only two ingeniously designed primers and only one recognition site of MSRE for the detection of DNA methylation. Differentiated by MSRE digestion, the cleaved unmethylated DNA is too short to induce any amplification reactions, while methylated DNA remains intact to trigger cascade exponential amplification and the subsequent CRISPR/Cas12a system. By integrating the two exponential amplification reactions, as low as 1 aM methylated DNA can be accurately detected, which corresponds to 6 molecules in a 10 μL system, indicating that our method is more sensitive than single amplification-based methods with the ability to detect DNA methylation at the single-molecule level. In addition, 0.1% methylated DNA can be effectively distinguished from large amounts of unmethylated DNA. Our method is further introduced to exploit the expression difference of DNA methylation among normal cells and cancer cells. Moreover, the visual detection of DNA methylation is also realized by the full hybridization between amplification products and the crRNA of CRISPR/Cas12a. Therefore, the proposed method has great potential to be a promising and robust bisulfite-free method for the detection of DNA methylation at the single-molecule level, which is of great importance for early diagnosis of cancer.

Increased [18F]FDG uptake of radiation-induced giant cells: a single-cell study in lung cancer models

Positron emission tomography (PET), a cornerstone in cancer diagnosis and treatment monitoring, relies on the enhanced uptake of fluorodeoxyglucose ([18F]FDG) by cancer cells to highlight tumors and other malignancies. While instrumental in the clinical setting, the accuracy of [18F]FDG-PET is susceptible to metabolic changes introduced by radiation therapy. Specifically, radiation induces the formation of giant cells, whose metabolic characteristics and [18F]FDG uptake patterns are not fully understood. Through a novel single-cell gamma counting methodology, we characterized the [18F]FDG uptake of giant A549 and H1299 lung cancer cells that were induced by radiation, and found it to be considerably higher than that of their non-giant counterparts. This observation was further validated in tumor-bearing mice, which similarly demonstrated increased [18F]FDG uptake in radiation-induced giant cells. These findings underscore the metabolic implications of radiation-induced giant cells, as their enhanced [18F]FDG uptake could potentially obfuscate the interpretation of [18F]FDG-PET scans in patients who have recently undergone radiation therapy.

Nanoengineering Solutions for Cancer Therapy: Bridging the Gap between Clinical Practice and Translational Research.

Nanoengineering has emerged as a progressive method in cancer treatment, offering precise and targeted delivery of therapeutic agents while concurrently reducing overall toxicity. This scholarly article delves into the innovative strategies and advancements in nanoengineering that bridge the gap between clinical practice and research in the field of cancer treatment. Various nanoengineered platforms such as nanoparticles, liposomes, and dendrimers are scrutinized for their capacity to encapsulate drugs, augment drug efficacy, and enhance pharmacokinetics. Moreover, the article investigates research breakthroughs that drive the progression and enhancement of nanoengineered remedies, encompassing the identification of biomarkers, establishment of preclinical models, and advancement of biomaterials, all of which are imperative for translating laboratory findings into practical medical interventions. Furthermore, the integration of nanotechnology with imaging modalities, which amplify cancer detection, treatment monitoring, and response assessment, is thoroughly examined. Finally, the obstacles and prospective directions in nanoengineering, including regulatory challenges and issues related to scalability, are examined. This underscores the significance of fostering collaboration among various entities in order to efficiently translate nanoengineered interventions into enhanced cancer therapies and patient management.

Ultra-short circulating tumor DNA (usctDNA): A new paradigm for ctDNA liquid biopsy.

e20510 Background: Mononucleosomal ctDNA (mnctDNA, 157-bp, double-stranded) spearheads liquid biopsy (LB) for cancer detection, treatment and clinical care. The bottleneck of mnctDNA LB are low copy number of ctDNA and limit of detection of platform technologies. Recent discovery of ultra-short ctDNA (usctDNA, 52-54 nt, single-stranded) that harbors somatic mutations prompted us to explore the quantification and stoichiometry of usctDNA to mnctDNA in plasma and saliva of NSCLC patients. Methods: Paired plasma and saliva from 20 advanced NSCLC patients with tissue genotyped positive for L858R were processed for cfDNA extraction and quantification with Qubit and Tape Station. Digital PCR assays targeting L858R somatic mutation to generate amplicons of 57-bp (usctDNA) and 100-bp (mnctDNA) were performed by UCLA and independently by NIST. Results: Results in Table 1 revealed that three findings of usctDNA that will have potential to impact ctDNA liquid biopsy. First, the somatic mutation (L858R) is present in usctDNA. Second, The stoichiometric ratio of usctDNA to mnctDNA is similar in plasma and saliva at 1.6X. For the wild-type counterpart, the ratio is 1.1X for plasma and 0.6X for saliva. Third, the copy number of usctDNA and mnctDNA in saliva to plasma is 7.8X and 7.7X. Conclusions: Detection of tumor-associated/specific EGFR L858R somatic mutations in uscfDNA is translationally impactful, adding 1.6X of the ctDNA targets for molecular detection, effectively cumulating 2.6X of total ctDNA targets, permitting earlier cancer detection, treatment monitoring and therapy prognostication. The finding that saliva harbors 7X of the us- and mnctDNA further raises the prospect of advancing saliva ctDNA liquid biopsy for NSCLC detection as it may effectively allow 15.5X (7.8X+7.7X) ability to detect malignancy-associated ctDNA. [Table: see text]

A web-based, LLM-powered AI symptom summarization tool (ASST) for monitoring of breast cancer treatment toxicity.

e13622 Background: Traditional methods for capturing patient-reported outcomes (PROs) are often time-consuming and may lead to underreporting of symptoms by physicians. With advancements in artificial intelligence (AI), particularly large language models (LLMs) like GPT-4, there is potential to revolutionize this aspect of patient care. Methods: This study developed and tested a GPT-4-based web application for monitoring cancer treatment toxicity in breast cancer patients. The application utilized 35 items from the PRO-CTCAE scale to create an interactive form for patients to report treatment-related symptoms. Upon form completion, a natural language summary of the patient’s responses was generated using the GPT-4 API for physician review. Nine radiation oncologists (5 attendings, 4 residents) evaluated the summaries of virtual patients using the adapted Physician Documentation Quality Index (PDQI-9). PDQI-9 consists of 9 items scored using a 5-point Likert scale (1 -not at all- to 5. -extremely-). IRB approval was not required because this study did not use real patient data, in accordance with the 2018 Revised Common Rule Requirements of the NIH. All data used were researcher-generated and non-identifiable. Results: The mean time for textual summary generation was 7 (5.7-9.2) seconds. The AI-Symptom Summarization Tool (ASST) mean scores were 4.25 for accuracy and 4 for thoroughness. Usefulness, organization, comprehensibility, concision, synthesis quality and consistency were all rated between 3 and 4. Overall score was 42/50. No hallucinations (false information made up by the LLM) were found. Conclusions: The GPT-4-based application for cancer treatment toxicity monitoring demonstrates significant promise in enhancing the quality and efficiency of patient care. By automating the documentation of patient-reported symptoms, this tool could allow physicians to focus more time on patient interaction and individualized care. As AI technologies continue to evolve, their integration into clinical practice must be approached with caution, emphasizing augmentation over replacement and the importance of verification to maintain trust in these new tools.