RESUMEN
The rapid advancements in large language models (LLMs) such as ChatGPT have raised concerns about their potential impact on academic integrity. While initial concerns focused on ChatGPT's writing capabilities, recent updates have integrated DALL-E 3's image generation features, extending the risks to visual evidence in biomedical research. Our tests revealed ChatGPT's nearly barrier-free image generation feature can be used to generate experimental result images, such as blood smears, Western Blot, immunofluorescence and so on. Although the current ability of ChatGPT to generate experimental images is limited, the risk of misuse is evident. This development underscores the need for immediate action. We suggest that AI providers restrict the generation of experimental image, develop tools to detect AI-generated images, and consider adding "invisible watermarks" to the generated images. By implementing these measures, we can better ensure the responsible use of AI technology in academic research and maintain the integrity of scientific evidence.
Asunto(s)
Investigación Biomédica , Humanos , Investigación Biomédica/métodos , Procesamiento de Imagen Asistido por Computador/métodos , Inteligencia Artificial , Programas InformáticosRESUMEN
This study evaluated the capabilities of the newly released ChatGPT-4V, a large language model with visual recognition abilities, in interpreting electrocardiogram waveforms and answering related multiple-choice questions for assisting with cardiovascular care.
Asunto(s)
Electrocardiografía , Electrocardiografía/métodos , Inteligencia ArtificialRESUMEN
Prostate cancer (PCa) is a common malignancy in males. The pathology review of PCa is crucial for clinical decision-making, but traditional pathology review is labor intensive and subjective to some extent. Digital pathology and whole-slide imaging enable the application of artificial intelligence (AI) in pathology. This review highlights the success of AI in detecting and grading PCa, predicting patient outcomes, and identifying molecular subtypes. We propose that AI-based methods could collaborate with pathologists to reduce workload and assist clinicians in formulating treatment recommendations. We also introduce the general process and challenges in developing AI pathology models for PCa. Importantly, we summarize publicly available datasets and open-source codes to facilitate the utilization of existing data and the comparison of the performance of different models to improve future studies.
Asunto(s)
Inteligencia Artificial , Neoplasias de la Próstata , Masculino , Humanos , Toma de Decisiones ClínicasRESUMEN
The increasing interest in the potential applications of generative artificial intelligence (AI) models like ChatGPT in health care has prompted numerous studies to explore its performance in various medical contexts. However, evaluating ChatGPT poses unique challenges due to the inherent randomness in its responses. Unlike traditional AI models, ChatGPT generates different responses for the same input, making it imperative to assess its stability through repetition. This commentary highlights the importance of including repetition in the evaluation of ChatGPT to ensure the reliability of conclusions drawn from its performance. Similar to biological experiments, which often require multiple repetitions for validity, we argue that assessing generative AI models like ChatGPT demands a similar approach. Failure to acknowledge the impact of repetition can lead to biased conclusions and undermine the credibility of research findings. We urge researchers to incorporate appropriate repetition in their studies from the outset and transparently report their methods to enhance the robustness and reproducibility of findings in this rapidly evolving field.
Asunto(s)
Inteligencia Artificial , Humanos , Inteligencia Artificial/tendencias , Inteligencia Artificial/normas , Reproducibilidad de los ResultadosRESUMEN
Background: This study was designed to evaluate the effects of body mass index (BMI) and weight change on the risk of developing cancer overall and cancer at different sites. Methods: We searched PubMed and other databases up to July 2023 using the keywords related to 'risk', 'cancer', 'weight', 'overweight', and 'obesity'. We identified eligible studies, and the inclusion criteria encompassed cohort studies in English that focused on cancer diagnosis and included BMI or weight change as an exposure factor. Multiple authors performed data extraction and quality assessment, and statistical analyses were carried out using RevMan and R software. We used random- or fixed-effects models to calculate the pooled relative risk (RR) or hazard ratio along with 95% confidence intervals (CIs). We used the Newcastle-Ottawa Scale to assess study quality. Results: Analysis included 66 cohort studies. Compared to underweight or normal weight, overweight or obesity was associated with an increased risk of endometrial cancer, kidney cancer, and liver cancer but a decreased risk of prostate cancer and lung cancer. Being underweight was associated with an increased risk of gastric cancer and lung cancer but not that of postmenopausal breast cancer or female reproductive cancer. In addition, weight loss of more than five kg was protective against overall cancer risk. Conclusions: Overweight and obesity increase the risk of most cancers, and weight loss of >5 kg reduces overall cancer risk. These findings provide insights for cancer prevention and help to elucidate the mechanisms underlying cancer development. Registration: Reviewregistry1786.
Asunto(s)
Índice de Masa Corporal , Neoplasias , Humanos , Neoplasias/epidemiología , Estudios de Cohortes , Obesidad/epidemiología , Factores de Riesgo , Sobrepeso/epidemiología , Pérdida de PesoRESUMEN
BACKGROUND: The introduction of ChatGPT-4V's 'Chat with images' feature represents the beginning of the era of large multimodal models (LMMs), which allows ChatGPT to process and answer questions based on uploaded images. This advancement has the potential to transform how surgical teams utilize radiographic data, as radiological interpretation is crucial for surgical planning and postoperative care. However, a comprehensive evaluation of ChatGPT-4V's capabilities in interpret radiological images and formulating treatment plans remains to be explored. PATIENTS AND METHODS: Three types of questions were collected: (1) 87 USMLE-style questions, submitting only the question stems and images without providing options to assess ChatGPT's diagnostic capability. For questions involving treatment plan formulations, a five-point Likert scale was used to assess ChatGPT's proposed treatment plan. The 87 questions were then adapted by removing detailed patient history to assess its contribution to diagnosis. The diagnostic performance of ChatGPT-4V was also tested when only medical history was provided. (2) We randomly selected 100 chest radiography from the ChestX-ray8 database to test the ability of ChatGPT-4V to identify abnormal chest radiography. (3) Cases from the 'Diagnose Please' section in the Radiology journal were collected to evaluate the performance of ChatGPT-4V in diagnosing complex cases. Three responses were collected for each question. RESULTS: ChatGPT-4V achieved a diagnostic accuracy of 77.01% for USMLE-style questions. The average score of ChatGPT-4V's treatment plans was 3.97 (Interquartile Range: 3.33-4.67). Removing detailed patient history dropped the diagnostic accuracy to 19.54% (P<0.0001). ChatGPT-4V achieved an AUC of 0.768 (95% CI: 0.684-0.851) in detecting abnormalities in chest radiography, but could not specify the exact disease due to the lack of detailed patient history. For cases from 'Diagnose Please' ChatGPT provided diagnoses consistent with or very similar to the reference answers. CONCLUSION: ChatGPT-4V demonstrated an impressive ability to combine patient history with radiological images to make diagnoses and directly design treatment plans based on images, suggesting its potential for future application in clinical practice.
Asunto(s)
Inteligencia Artificial , Interpretación de Imagen Asistida por Computador , Radiografía , Humanos , Proyectos Piloto , Simulación por ComputadorRESUMEN
The recent integration of the latest image generation model DALL-E 3 into ChatGPT allows text prompts to easily generate the corresponding images, enabling multimodal output from ChatGPT. We explored the feasibility of DALL-E 3 for drawing a 12-lead ECG and found that it can draw rudimentary 12-lead electrocardiograms (ECG) displaying some of the parameters, although the details are not completely accurate. We also explored DALL-E 3's capacity to create vivid illustrations for teaching resuscitation-related medical knowledge. DALL-E 3 produced accurate CPR illustrations emphasizing proper hand placement and technique. For ECG principles, it produced creative heart-shaped waveforms tying ECGs to the heart. With further training, DALL-E 3 shows promise to expand easy-to-understand visual medical teaching materials and ECG simulations for different disease states. In conclusion, DALL-E 3 has the potential to generate realistic 12-lead ECGs and teaching schematics, but expert validation is still needed.
RESUMEN
Background: Small-cell lung cancer (SCLC) is characterized by its high malignancy and is associated with a poor prognosis. In the early stages of the disease, platinum-based chemotherapy is the recommended first-line treatment and has demonstrated efficacy. However, SCLC is prone to recurrence and is generally resistant to chemotherapy in its later stages. Methods: Here, we collected samples from SCLC patients who received platinum-based chemotherapy, performed genomic and transcriptomic analyses, and validated our results with publicly available data. Results: SCLC patients with DNA polymerase binding pathway mutations had an improved prognosis after platinum chemotherapy compared with patients without such mutations. Patients in the mutant (MT) group had higher infiltration of T cells, B cells, and M1 macrophages compared with patients without DNA polymerase binding pathway mutations. Conclusions: DNA polymerase binding pathway mutations can be used as prognostic markers for platinum-based chemotherapy in SCLC.
RESUMEN
BACKGROUND: The early detection of high-grade prostate cancer (HGPCa) is of great importance. However, the current detection strategies result in a high rate of negative biopsies and high medical costs. In this study, the authors aimed to establish an Asian Prostate Cancer Artificial intelligence (APCA) score with no extra cost other than routine health check-ups to predict the risk of HGPCa. PATIENTS AND METHODS: A total of 7476 patients with routine health check-up data who underwent prostate biopsies from January 2008 to December 2021 in eight referral centres in Asia were screened. After data pre-processing and cleaning, 5037 patients and 117 features were analyzed. Seven AI-based algorithms were tested for feature selection and seven AI-based algorithms were tested for classification, with the best combination applied for model construction. The APAC score was established in the CH cohort and validated in a multi-centre cohort and in each validation cohort to evaluate its generalizability in different Asian regions. The performance of the models was evaluated using area under the receiver operating characteristic curve (ROC), calibration plot, and decision curve analyses. RESULTS: Eighteen features were involved in the APCA score predicting HGPCa, with some of these markers not previously used in prostate cancer diagnosis. The area under the curve (AUC) was 0.76 (95% CI:0.74-0.78) in the multi-centre validation cohort and the increment of AUC (APCA vs. PSA) was 0.16 (95% CI:0.13-0.20). The calibration plots yielded a high degree of coherence and the decision curve analysis yielded a higher net clinical benefit. Applying the APCA score could reduce unnecessary biopsies by 20.2% and 38.4%, at the risk of missing 5.0% and 10.0% of HGPCa cases in the multi-centre validation cohort, respectively. CONCLUSIONS: The APCA score based on routine health check-ups could reduce unnecessary prostate biopsies without additional examinations in Asian populations. Further prospective population-based studies are warranted to confirm these results.
Asunto(s)
Antígeno Prostático Específico , Neoplasias de la Próstata , Masculino , Humanos , Inteligencia Artificial , Clasificación del Tumor , Medición de Riesgo/métodos , Neoplasias de la Próstata/diagnóstico , Biopsia , Curva ROCRESUMEN
The study by Fijacko et al. tested ChatGPT's ability to pass the BLS and ACLS exams of AHA, but found that ChatGPT failed both exams. A limitation of their study was using ChatGPT to generate only one response, which may have introduced bias. When generating three responses per question, ChatGPT can pass BLS exam with an overall accuracy of 84%. When incorrectly answered questions were rewritten as open-ended questions, ChatGPT's accuracy rate increased to 96% and 92.1% for the BLS and ACLS exams, respectively, allowing ChatGPT to pass both exams with outstanding results.
Asunto(s)
Lenguaje , Neoplasias de la Próstata , Masculino , Humanos , Bases de Datos Factuales , ConocimientoRESUMEN
Researches show that chronic viral infection and persistent antigen and/or inflammatory signal exposure in cancer causes the functional status of T cells to be altered, mainly by major changes in the epigenetic and metabolic environment, which then leads to T cell exhaustion. The discovery of the immune checkpoint pathway is an important milestone in understanding and reversing T cell exhaustion. Antibodies targeting these pathways have shown superior ability to reverse T cell exhaustion. However, there are still some limitations in immune checkpoint blocking therapy, such as the short-term nature of therapeutic effects and high individual heterogeneity. Assay for transposase-accessible chromatin with sequencing(ATAC-seq) is a method used to analyze the accessibility of whole-genome chromatin. It uses hyperactive Tn5 transposase to assess chromatin accessibility. Recently, a growing number of studies have reported that ATAC-seq can be used to characterize the dynamic changes of epigenetics in the process of T cell exhaustion. It has been determined that immune checkpoint blocking can only temporarily restore the function of exhausted T cells because of an irreversible change in the epigenetics of exhausted T cells. In this study, we review the latest developments, which provide a clearer molecular understanding of T cell exhaustion, reveal potential new therapeutic targets for persistent viral infection and cancer, and provide new insights for designing effective immunotherapy for treating cancer and chronic infection.
Asunto(s)
Secuenciación de Inmunoprecipitación de Cromatina , Neoplasias , Humanos , Agotamiento de Células T , Secuenciación de Nucleótidos de Alto Rendimiento/métodos , Cromatina/genética , Neoplasias/genética , Neoplasias/terapiaRESUMEN
BACKGROUND: Colon adenocarcinoma (COAD) is one of the major varieties of malignant tumors threatening human health today. Immune checkpoint inhibitors (ICIs) have recently begun to emerge as an effective option for the treatment of COAD patients, but not all patients can benefit from ICI treatment. Previous studies have suggested that ICIs boast significant clinical effects on patients with microsatellite instability-high (MSI-H), while conversely patients with microsatellite-stable/microsatellite instability-low (MSS/MSI-L) have shown limited response. METHODS: We used ATAC-seq, RNA-seq, and mutation data from The Cancer Genome Atlas Colon adenocarcinoma (TCGA-COAD) cohort to perform multi-omics differential analysis on COAD samples with different MSI statuses, then further screened genes by additionally combining these results with survival analysis. We analyzed the effects of the screened genes on the tumor microenvironment and immunogenicity of COAD patients, and subsequently determined their influence on the efficacy of ICIs in COAD patients using a series of predictive indexes. RESULTS: Twelve genes were screened in the TCGA-COAD cohort, and after the combined survival analysis, we identified ATOH1 as having significant effects. ATOH1 is characterized by high chromatin accessibility, high expression, and high mutation in COAD patients in the MSI-H group. COAD patients with high ATOH1 expression are associated with a better prognosis, unique immune microenvironment, and higher efficacy in ICI treatment. Enrichment analysis showed that COAD patients with high ATOH1 expression displayed significant upregulation in their humoral immunity and other related pathways. CONCLUSIONS: We speculate that ATOH1 may influence the efficacy of ICIs therapy in patients with COAD by affecting the immune microenvironment and immunogenicity of the tumor.
RESUMEN
Background: Platinum-based chemotherapy is the first choice of treatment for patients diagnosed with small lung cell cancer (SCLC). However, many patients exhibit resistance to it. Therefore, it is imperative to further investigate a prognostic biomarker indicating sensitivity to this therapy. Methods: We collected and performed RNA sequencing on 45 SCLC samples from the Zhujiang Hospital (Local-SCLC). In addition, we used a public cohort from George et al. as a validation cohort (George-SCLC). The transforming growth factor ß signaling pathway (TGFB) activation status was determined according to the related ssGSEA score. We analyzed immune cell ratios, pathway activation scores, and immune-related genes in SCLC patients to further elucidate the potential mechanisms. Results: A high activation status of the TGFB pathway was associated with improved prognosis in SCLC patients receiving platinum-based chemotherapy (Local-SCLC: HR = 0.0238, (95% CI, 0.13-0.84), p = 0.0238; George-SCLC: HR = 0.0315, (95% CI, 0.28-0.98), p = 0.0315). Immune infiltration analysis showed that the TGFB-HIGH group had more M1 macrophages and Th1 cells, whilst fewer M2 macrophages, Th2 cells, and Treg cells were found in the Local-SCLC cohort. Mechanistic analysis showed that the TGBF-HIGH group was upregulated in STING-mediated immunity, apoptosis, and cell cycle arrest, as well as being downregulated in the process of DNA damage repair. Conclusions: SCLC patients exhibiting a high activation status of the TGFB pathway demonstrate an improved prognosis with platinum-based chemotherapy. The potential underlying mechanism may be related to antitumor immune enhancement and DNA damage repair inhibition.
Asunto(s)
Carcinoma de Células Pequeñas , Neoplasias Pulmonares , Carcinoma Pulmonar de Células Pequeñas , Humanos , Carcinoma Pulmonar de Células Pequeñas/tratamiento farmacológico , Carcinoma Pulmonar de Células Pequeñas/genética , Neoplasias Pulmonares/tratamiento farmacológico , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/patología , Platino (Metal)/uso terapéutico , PronósticoRESUMEN
Immune checkpoint inhibitors (ICIs) have changed the treatment paradigm of metastatic urothelial carcinoma (mUC), a dominant type of bladder cancer (BC). Previous studies have shown an association between gene mutations in the DNA damage response (DDR) pathway and the immunotherapy response in mUC but have neglected the effect of the activation level of the DDR pathway on the ICI response in mUC. A published immunotherapy cohort with genome, transcriptome and survival data for 348 mUC patients was used. An external cohort (The Cancer Genome Atlas Bladder Cancer) and the GSE78220 cohort were used for validation. The activation level of the DDR pathway was quantified using single-sample gene set enrichment analysis (ssGSEA). Further analysis on the genome, immunogenicity, and the immune microenvironment was conducted using the DDR ssGSEA enrichment score-high (DSSH) group and the DDR ssGSEA enrichment score-low (DSSL) group. In the mUC cohorts, the DSSH group was associated with longer overall survival times (P=0.026; Hazard ratio=0.67; 95%CI: 0.46-0.95). The DSSH group was also associated with higher tumor mutation burden, neoantigen load, immune-activated cell patterns, and immune-related gene expression levels. The GSEA results indicated an immune activation state in DSSH group, which correlated with a down-regulation in the transforming growth factor ß receptor signaling pathway. Our study suggests that the activation level of the DDR pathway may be a novel predictive marker for immunotherapy efficacy in patients with mUC.