-
Journal of Multidisciplinary Healthcare 2024The incidence of cancer is increasing, and cancer survivors are also growing exponentially. Cancer is defined as a new chronic disease. Nevertheless, the management of...
BACKGROUND
The incidence of cancer is increasing, and cancer survivors are also growing exponentially. Cancer is defined as a new chronic disease. Nevertheless, the management of cancer in the form of chronic diseases in China is still in its infancy, without a standardized care model.
OBJECTIVE
This study aimed to explore the current status of management of cancer care from the patient's perspective.
METHODS
This cross-sectional study was a questionnaire survey of patients diagnosed with cancer, including information of the current situation of daily medical consultation, status of comorbidity, and expectations of seeking cancer care in future. Chi-square test and logistic regression analysis were used to explore the factors influencing patients' choice of cancer management mode.
RESULTS
A total of 200 cancer patients were included in the study. The majority (n = 150) of cancer patients chose an oncologist in a tertiary hospital for cancer care. Difficulty in registration (45%), time-consuming (34.5%), repeated examinations (34.5%) and different treatment opinions (12.0%) were the main difficulties they encountered currently during tertiary hospital visits. In community hospital, lack of trust in general practitioners (n = 33) and the necessary drugs or testing items in community hospitals (n = 47) were the main difficulties during their visits. Logistic regression analysis showed that male (OR = 2.737, 95% CI, 1.332-5.627, p = 0.006) and elderly patients (OR = 3.186, 95% CI, 1.172-8.661, p = 0.023) were more likely to choose general practitioners (GPs) in community hospitals. Twenty-nine (14.5%) patients hope to have an integrated multidisciplinary management in tertiary and community hospitals with the active participation of GPs for cancer care.
CONCLUSION
Improving drug availability, equipment and quality of cancer care services can help to increase cancer patients' recognition of community hospital. In addition, the multidisciplinary management integrated tertiary hospitals and communities with the participation of GPs is a worth exploring mode that improves the management of cancer care.
PubMed: 38881752
DOI: 10.2147/JMDH.S460881 -
JMIR AI Jan 2024ChatGPT (Open AI) is a state-of-the-art large language model that uses artificial intelligence (AI) to address questions across diverse topics. The American Society of...
BACKGROUND
ChatGPT (Open AI) is a state-of-the-art large language model that uses artificial intelligence (AI) to address questions across diverse topics. The American Society of Clinical Oncology Self-Evaluation Program (ASCO-SEP) created a comprehensive educational program to help physicians keep up to date with the many rapid advances in the field. The question bank consists of multiple choice questions addressing the many facets of cancer care, including diagnosis, treatment, and supportive care. As ChatGPT applications rapidly expand, it becomes vital to ascertain if the knowledge of ChatGPT-3.5 matches the established standards that oncologists are recommended to follow.
OBJECTIVE
This study aims to evaluate whether ChatGPT-3.5's knowledge aligns with the established benchmarks that oncologists are expected to adhere to. This will furnish us with a deeper understanding of the potential applications of this tool as a support for clinical decision-making.
METHODS
We conducted a systematic assessment of the performance of ChatGPT-3.5 on the ASCO-SEP, the leading educational and assessment tool for medical oncologists in training and practice. Over 1000 multiple choice questions covering the spectrum of cancer care were extracted. Questions were categorized by cancer type or discipline, with subcategorization as treatment, diagnosis, or other. Answers were scored as correct if ChatGPT-3.5 selected the answer as defined by ASCO-SEP.
RESULTS
Overall, ChatGPT-3.5 achieved a score of 56.1% (583/1040) for the correct answers provided. The program demonstrated varying levels of accuracy across cancer types or disciplines. The highest accuracy was observed in questions related to developmental therapeutics (8/10; 80% correct), while the lowest accuracy was observed in questions related to gastrointestinal cancer (102/209; 48.8% correct). There was no significant difference in the program's performance across the predefined subcategories of diagnosis, treatment, and other (P=.16, which is greater than .05).
CONCLUSIONS
This study evaluated ChatGPT-3.5's oncology knowledge using the ASCO-SEP, aiming to address uncertainties regarding AI tools like ChatGPT in clinical decision-making. Our findings suggest that while ChatGPT-3.5 offers a hopeful outlook for AI in oncology, its present performance in ASCO-SEP tests necessitates further refinement to reach the requisite competency levels. Future assessments could explore ChatGPT's clinical decision support capabilities with real-world clinical scenarios, its ease of integration into medical workflows, and its potential to foster interdisciplinary collaboration and patient engagement in health care settings.
PubMed: 38875575
DOI: 10.2196/50442 -
JMIR AI May 2023The identification of objective pain biomarkers can contribute to an improved understanding of pain, as well as its prognosis and better management. Hence, it has the...
A Scalable Radiomics- and Natural Language Processing-Based Machine Learning Pipeline to Distinguish Between Painful and Painless Thoracic Spinal Bone Metastases: Retrospective Algorithm Development and Validation Study.
BACKGROUND
The identification of objective pain biomarkers can contribute to an improved understanding of pain, as well as its prognosis and better management. Hence, it has the potential to improve the quality of life of patients with cancer. Artificial intelligence can aid in the extraction of objective pain biomarkers for patients with cancer with bone metastases (BMs).
OBJECTIVE
This study aimed to develop and evaluate a scalable natural language processing (NLP)- and radiomics-based machine learning pipeline to differentiate between painless and painful BM lesions in simulation computed tomography (CT) images using imaging features (biomarkers) extracted from lesion center point-based regions of interest (ROIs).
METHODS
Patients treated at our comprehensive cancer center who received palliative radiotherapy for thoracic spine BM between January 2016 and September 2019 were included in this retrospective study. Physician-reported pain scores were extracted automatically from radiation oncology consultation notes using an NLP pipeline. BM center points were manually pinpointed on CT images by radiation oncologists. Nested ROIs with various diameters were automatically delineated around these expert-identified BM center points, and radiomics features were extracted from each ROI. Synthetic Minority Oversampling Technique resampling, the Least Absolute Shrinkage And Selection Operator feature selection method, and various machine learning classifiers were evaluated using precision, recall, F-score, and area under the receiver operating characteristic curve.
RESULTS
Radiation therapy consultation notes and simulation CT images of 176 patients (mean age 66, SD 14 years; 95 males) with thoracic spine BM were included in this study. After BM center point identification, 107 radiomics features were extracted from each spherical ROI using pyradiomics. Data were divided into 70% and 30% training and hold-out test sets, respectively. In the test set, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of our best performing model (neural network classifier on an ensemble ROI) were 0.82 (132/163), 0.59 (16/27), 0.85 (116/136), and 0.83, respectively.
CONCLUSIONS
Our NLP- and radiomics-based machine learning pipeline was successful in differentiating between painful and painless BM lesions. It is intrinsically scalable by using NLP to extract pain scores from clinical notes and by requiring only center points to identify BM lesions in CT images.
PubMed: 38875572
DOI: 10.2196/44779 -
The Oncologist Jun 2024This is a phase II subprotocol of the NCI-COG Pediatric MATCH study evaluating vemurafenib, a selective oral inhibitor of BRAF V600 mutated kinase, in patients with...
BACKGROUND
This is a phase II subprotocol of the NCI-COG Pediatric MATCH study evaluating vemurafenib, a selective oral inhibitor of BRAF V600 mutated kinase, in patients with relapsed or refractory solid tumors harboring BRAF V600 mutations.
METHODS
Patients received vemurafenib at 550 mg/m2 (maximum 960 mg/dose) orally twice daily for 28-day cycles until progression or intolerable toxicity. The primary aim was to determine the objective response rate and secondary objectives included estimating progression-free survival and assessing the tolerability of vemurafenib.
RESULTS
Twenty-two patients matched to the subprotocol and 4 patients (18%) enrolled. Primary reasons for non-enrollment were ineligibility due to exclusions of low-grade glioma (nâ=â7) and prior BRAF inhibitor therapy (nâ=â7). Enrolled diagnoses were one each of histiocytosis, ameloblastoma, Ewing sarcoma, and high-grade glioma, all with BRAF V600E mutations. Treatment was overall tolerable with mostly expected grade 1/2 adverse events (AE). Grade 3 or 4 AE on treatment were acute kidney injury, hyperglycemia, and maculopapular rash. One patient came off therapy due to AE. One patient (glioma) had an objective partial response and remained on protocol therapy for 15 cycles.
CONCLUSION
There was a low accrual rate on this MATCH subprotocol, with only 18% of those who matched with BRAFV600 mutations enrolling, resulting in early termination, and limiting study results (ClinicalTrials.gov Identifier: NCT03220035).
PubMed: 38873934
DOI: 10.1093/oncolo/oyae119 -
Communications Medicine Jun 2024Chimeric antigen receptor (CAR) T-cell therapy and bispecific T-cell engagers, which redirect T-cells to tumor antigens, have immensely benefitted patients with...
BACKGROUND
Chimeric antigen receptor (CAR) T-cell therapy and bispecific T-cell engagers, which redirect T-cells to tumor antigens, have immensely benefitted patients with relapsed/refractory B-cell cancers. How these therapies differ in cardiotoxicity is underexplored. We used the World Health Organization pharmacovigilance database, VigiBase, to compare cardiotoxicity profiles between CD19-targeted CAR-T therapy and blinatumomab (a CD19/CD3-targeted bispecific T-cell engager).
METHODS
Safety reports in VigiBase were filtered for diffuse large B-cell lymphoma (DLBCL, n = 17,479) and acute lymphocytic leukemia (ALL, n = 28,803) for all adverse reactions. Data were further filtered for patients taking CAR-T therapy or blinatumomab. Reporting odds ratios (ROR) and fatality rates were compared between CAR-T cell products (e.g. tisagenlecleucel and axicabtagene ciloleucel), and between CAR-T therapy and blinatumomab.
RESULTS
Tisagenlecleucel is associated with cardiac failure (IC = 0.366) with fatality rates of 85.7% and 80.0% in DLBCL and pediatric ALL patients respectively. For DLBCL patients, axicabtagene ciloleucel has greater reporting for hypotension than tisagenlecleucel (ROR: 2.54; 95% CI: 1.28-5.03; p = 0.012), but tisagenlecleucel has higher fatality rates for hypotension than axicabtagene ciloleucel [50.0% (tisagenlecleucel) vs 5.6% (axicabtagene ciloleucel); p < 0.001]. Blinatumomab and tisagenlecleucel have similar fatality rates for hypotension in pediatric ALL patients [34.7% (tisagenlecleucel) vs 20.0% (blinatumomab); p = 0.66].
CONCLUSIONS
Tisagenlecleucel is associated with severe and fatal adverse cardiac events, with higher fatality rates for hypotension compared to axicabtagene ciloleucel in DLBCL patients, but similar hypotension fatality rates compared to blinatumomab in pediatric ALL patients. Effective management necessitates experienced physicians, including cardio-oncologists, skilled in interdisciplinary approaches to manage these toxicities.
PubMed: 38871977
DOI: 10.1038/s43856-024-00540-9 -
Journal of Hepatology Jun 2024Primary liver tumours, including benign liver tumours, hepatocellular carcinoma and cholangiocarcinoma, present a multifaceted challenge, necessitating a collaborative... (Review)
Review
Primary liver tumours, including benign liver tumours, hepatocellular carcinoma and cholangiocarcinoma, present a multifaceted challenge, necessitating a collaborative approach, as evidenced by the role of the multidisciplinary tumour board (MDTB). The approach to managing primary liver tumours gathers specialized teams, including surgeons, radiologists, oncologists, pathologists, hepatologists, and radiation oncologists, to propose individualized treatment plans. The evolving landscape of primary liver cancer treatment introduces complexities, particularly with the expanding array of systemic and locoregional therapies, alongside the potential integration of molecular biology and artificial intelligence (AI) into MDTB in the future. Precision medicine demands collaboration across disciplines, challenging traditional frameworks. The next decade anticipates the convergence of AI, molecular biology, pathology, and advanced imaging, requiring adaptability in MDTB structure to incorporate these cutting-edge technologies. Navigating this evolution also requires a focus on enhancing basic, translational, and clinical research, as well as boosting clinical trials through an upgraded use of MDTBs as hubs for scientific collaboration and raising literacy about AI and new technologies. In this review, we will delineate the current unmet needs in the clinical management of primary liver cancers, discuss our perspective on the future role of MDTBs in primary liver cancers ("next generation" MDTBs), and unravel the potential power and limitations of novel technologies that may shape the multidisciplinary care landscape for primary liver cancers in the coming decade.
PubMed: 38871125
DOI: 10.1016/j.jhep.2024.05.041 -
Cancer Treatment Reviews Jun 2024The detection of germline pathogenic variants (gPVs) in BRCA1/2 and other breast cancer (BC) genes is rising exponentially thanks to the advent of multi-gene panel... (Review)
Review
The detection of germline pathogenic variants (gPVs) in BRCA1/2 and other breast cancer (BC) genes is rising exponentially thanks to the advent of multi-gene panel testing. This promising technology, coupled with the availability of specific therapies for BC BRCA-related, has increased the number of patients eligible for genetic testing. Implementing multi-gene panel testing for hereditary BC screening holds promise to maximise benefits for patients at hereditary risk of BC. These benefits range from prevention programs to antineoplastic-targeted therapies. However, the clinical management of these patients is complex and requires guidelines based on recent evidence. Furthermore, applying multi-gene panel testing into clinical practice increases the detection of variants of uncertain significance (VUSs). This augments the complexity of patients' clinical management, becoming an unmet need for medical oncologists. This review aims to collect updated evidence on the most common BC-related genes besides BRCA1/2, from their biological role in BC development to their potential impact in tailoring prevention and treatment strategies.
PubMed: 38870570
DOI: 10.1016/j.ctrv.2024.102785 -
JCO Clinical Cancer Informatics Jun 2024The quality of radiotherapy auto-segmentation training data, primarily derived from clinician observers, is of utmost importance. However, the factors influencing the...
PURPOSE
The quality of radiotherapy auto-segmentation training data, primarily derived from clinician observers, is of utmost importance. However, the factors influencing the quality of clinician-derived segmentations are poorly understood; our study aims to quantify these factors.
METHODS
Organ at risk (OAR) and tumor-related segmentations provided by radiation oncologists from the Contouring Collaborative for Consensus in Radiation Oncology data set were used. Segmentations were derived from five disease sites: breast, sarcoma, head and neck (H&N), gynecologic (GYN), and GI. Segmentation quality was determined on a structure-by-structure basis by comparing the observer segmentations with an expert-derived consensus, which served as a reference standard benchmark. The Dice similarity coefficient (DSC) was primarily used as a metric for the comparisons. DSC was stratified into binary groups on the basis of structure-specific expert-derived interobserver variability (IOV) cutoffs. Generalized linear mixed-effects models using Bayesian estimation were used to investigate the association between demographic variables and the binarized DSC for each disease site. Variables with a highest density interval excluding zero were considered to substantially affect the outcome measure.
RESULTS
Five hundred seventy-four, 110, 452, 112, and 48 segmentations were used for the breast, sarcoma, H&N, GYN, and GI cases, respectively. The median percentage of segmentations that crossed the expert DSC IOV cutoff when stratified by structure type was 55% and 31% for OARs and tumors, respectively. Regression analysis revealed that the structure being tumor-related had a substantial negative impact on binarized DSC for the breast, sarcoma, H&N, and GI cases. There were no recurring relationships between segmentation quality and demographic variables across the cases, with most variables demonstrating large standard deviations.
CONCLUSION
Our study highlights substantial uncertainty surrounding conventionally presumed factors influencing segmentation quality relative to benchmarks.
Topics: Humans; Bayes Theorem; Benchmarking; Radiation Oncologists; Female; Radiotherapy Planning, Computer-Assisted; Neoplasms; Organs at Risk; Male; Radiation Oncology; Demography; Observer Variation
PubMed: 38870441
DOI: 10.1200/CCI.23.00174 -
The Oncologist Jun 2024Image-guided therapies (IGTs) are commonly used in oncology, but their role in adrenocortical carcinoma (ACC) is not well defined.
BACKGROUND
Image-guided therapies (IGTs) are commonly used in oncology, but their role in adrenocortical carcinoma (ACC) is not well defined.
MATERIALS AND METHODS
A retrospective review of patients with ACC treated with IGTs. We assessed response to therapy using RECIST v1.1, time to next line of systemic therapy, disease control rate (DCR), local tumor progression-free survival (LTPFS), and complications of IGTs (based on the Common Terminology Criteria for Adverse Events [CTCAE] version 5.0).
RESULTS
Our cohort included 26 patients (median age 56 years [range 38-76]; n = 18 female) who had 51 IGT sessions to treat 86 lesions. IGTs modalities included cryoablation (n = 49), microwave ablation (n = 21), combined microwave and bland trans-arterial embolization (n = 8), bland trans-arterial embolization alone (n = 3), radio-embolization (n = 3), and radiofrequency ablation (n = 2). DCR was 81.4% (70 out of 86), of which 66.3% of tumors showed complete response, 18.6% showed progressive disease, 8.1% showed partial response, and 7.0% showed stable disease. LTPFS rates were 73% and 63% at 1 and 2 years, respectively. Fourteen lesions underwent re-ablation for incomplete response on initial treatment. Sixteen patients (61.5%) received new systemic therapy following IGTs, with a median time to systemic therapy of 12.5 months (95% CI: 8.6 months upper limit not reached). There was 1 reported CTCAE grade 3 adverse event (biloma) following IGT.
CONCLUSIONS
IGT use in properly selected patients with ACC is safe and associated with prolonged disease control and delay in the need for systemic therapy.
PubMed: 38869364
DOI: 10.1093/oncolo/oyae130 -
The Oncologist Jun 2024Chemotherapy-induced alopecia is a common consequence of cancer treatment with a high psychological impact on patients and can be prevented by scalp cooling (SC). With...
BACKGROUND
Chemotherapy-induced alopecia is a common consequence of cancer treatment with a high psychological impact on patients and can be prevented by scalp cooling (SC). With this multi-center patient series, we examined the results for multiple currently used chemotherapy regimens to offer an audit into the real-world determinants of SC efficacy.
MATERIALS AND METHODS
The Dutch Scalp Cooling Registry collected data on 7424 scalp-cooled patients in 68 Dutch hospitals. Nurses and patients completed questionnaires on patient characteristics, chemotherapy, and SC protocol. Patient-reported primary outcomes at the start of the final SC session included head cover (HC) (eg, wig/scarf) use (yes/no) as a surrogate for patient satisfaction with SC and WHO score for alopecia (0 = no hair loss up to 3 = total alopecia) as a measure of scalp cooling success. Exhaustive logistic regression analysis stratified by chemotherapy regimen was implemented to examine characteristics and interactions associated with the SC result.
RESULTS
Overall, over half of patients (n = 4191, 56%) did not wear a HC and 53% (n = 3784/7183) reported minimal hair loss (WHO score 0/1) at the start of their final treatment. Outcomes were drug and dose dependent. Besides the chemotherapy regimen, this study did not identify any patient characteristic or lifestyle factor as a generic determinant influencing SC success. For non-gender specific cancers, gender played no statistically significant role in HC use nor WHO score.
CONCLUSIONS
Scalp cooling is effective for the majority of patients. The robust model for evaluating the drug and dose-specific determinants of SC efficacy revealed no indications for changes in daily practice, suggesting factors currently being overlooked. As no correlation was identified between the determinants explaining HC use and WHO score outcomes, new methods for evaluation are warranted.
PubMed: 38869252
DOI: 10.1093/oncolo/oyae116