RESUMO
Mutations in genes encoding transcription factors inactivate or generate ectopic activities to instigate pathogenesis. By disrupting hematopoietic stem/progenitor cells, GATA2 germline variants create a bone marrow failure and leukemia predisposition, GATA2 deficiency syndrome, yet mechanisms underlying the complex phenotypic constellation are unresolved. We used a GATA2-deficient progenitor rescue system to analyze how genetic variation influences GATA2 functions. Pathogenic variants impaired, without abrogating, GATA2-dependent transcriptional regulation. Variants promoted eosinophil and repressed monocytic differentiation without regulating mast cell and erythroid differentiation. While GATA2 and T354M required the DNA-binding C-terminal zinc finger, T354M disproportionately required the N-terminal finger and N terminus. GATA2 and T354M activated a CCAAT/Enhancer Binding Protein-ε (C/EBPε) enhancer, creating a feedforward loop operating with the T-cell Acute Lymphocyte Leukemia-1 (TAL1) transcription factor. Elevating C/EBPε partially normalized hematopoietic defects of GATA2-deficient progenitors. Thus, pathogenic germline variation discriminatively spares or compromises transcription factor attributes, and retaining an obligate enhancer mechanism distorts a multilineage differentiation program.
Assuntos
Leucemia , Sequências Reguladoras de Ácido Nucleico , Humanos , Diferenciação Celular/genética , Genótipo , Células-Tronco Hematopoéticas , Fator de Transcrição GATA2/genéticaRESUMO
Repeated chromatography of the CH2Cl2 and EtOAc soluble fractions from the methanol extract of Belamcanda chinensis root yielded six new sucrosephenylpropanoid esters (1-6) and twenty-one known compounds (7-27). The structures of 1-6 were elucidated using diverse nuclear magnetic resonance (NMR) techniques and high-resolution mass spectrometry (HRMS) data analysis, together with chemical methods. All the twenty-seven isolated compounds were evaluated for their anti-osteoclastogenic activities. Preliminary screening results revealed that compounds 1 and 19 exhibited strong effects against RANKL-induced osteoclast formation in RAW264.7 cells. In addition, the treatment of mouse bone marrow macrophages (BMMs) with compounds 1 and 19 significantly decreased RANKL-induced TRAP-positive multinucleated osteoclast formation in a concentration-dependent manner without affecting cell viability. Further bioassay investigation showed that compounds 1 and 19 inhibited the expression of some osteoclast-specific marker genes and the transcription factor nuclear factor of activated T cells cytoplasmic 1 (NFATc1) in response to RANKL. To the best of our knowledge, this is the first investigation of anti-osteoclastogenic activity for compounds isolated from B. chinensis.
Assuntos
Reabsorção Óssea , Isoflavonas , Animais , Camundongos , Reabsorção Óssea/tratamento farmacológico , Reabsorção Óssea/metabolismo , Reabsorção Óssea/prevenção & controle , Diferenciação Celular , Fatores de Transcrição NFATC/efeitos dos fármacos , Fatores de Transcrição NFATC/genética , Fatores de Transcrição NFATC/metabolismo , Osteoclastos , Osteogênese/efeitos dos fármacos , Isoflavonas/química , Isoflavonas/farmacologia , Raízes de Plantas/químicaRESUMO
Historically, Astragalus membranaceus Bunge has been used as a beneficial medicinal plant, particularly in the Asian traditional medical systems, for the treatment of various human diseases such as stomach ulcers, diarrhea, and respiratory issues associated with phlegm. In this study, a phytochemical characterization of the aerial parts of A. membranaceusled to the isolation of 29 oleanane-type triterpenoid saponins, including 11 new compounds named astraoleanosides E-P (6-9, 13, 14, 18-22), as well as 18 known ones. The structures of these compounds were elucidated using nuclear magnetic resonance (NMR) spectroscopy and high-resolution mass spectrometry. Among them, astraoleanoside H (9) and cloversaponin III (15) demonstrated the most potent ß-glucuronidase inhibitory activities, with IC50 values of 21.20 ± 0.75 and 9.05 ± 0.47 µM, respectively, compared to the positive control d-saccharic acid 1,4-lactone (IC50 = 20.62 ± 1.61 µM). Enzyme kinetics studies were then conducted to investigate the type of inhibition exhibited by these active compounds. In addition, the binding mechanism, key interactions, binding stability, and dynamic behavior of protein-ligand complexes were investigated through in silico approaches, such as molecular docking and molecular dynamics simulations. These findings highlight the promising potential of triterpenoid saponins from A. membranaceus as lead compounds for ß-glucuronidase inhibitors, offering new possibilities for the development of therapeutic agents targeting various diseases where ß-glucuronidase plays a crucial role.
Assuntos
Ácido Oleanólico , Ácido Oleanólico/análogos & derivados , Saponinas , Triterpenos , Humanos , Estrutura Molecular , Astragalus propinquus/química , Simulação de Acoplamento Molecular , Saponinas/química , Ácido Oleanólico/química , Componentes Aéreos da Planta/química , Triterpenos/farmacologia , Triterpenos/químicaRESUMO
During the coronavirus disease 2019 (COVID-19) pandemic, conclusively evaluating possible associations between COVID-19 vaccines and potential adverse events was of critical importance. The National Academy of Medicine of Korea established the COVID-19 Vaccine Safety Research Center (CoVaSC) with support from the Korea Disease Control and Prevention Agency to investigate the scientific relationship between COVID-19 vaccines and suspected adverse events. Although determining whether the COVID-19 vaccine was responsible for any suspected adverse event necessitated a systematic approach, traditional causal inference theories, such as Hill's criteria, encountered certain limitations and criticisms. To facilitate a systematic and evidence-based evaluation, the United States Institute of Medicine, at the request of the Centers for Disease Control and Prevention, offered a detailed causality assessment framework in 2012, which was updated in the recent report by the National Academies of Sciences, Engineering, and Medicine (NASEM) in 2024. This framework, based on a weight-of-evidence approach, allows the independent evaluation of both epidemiological and mechanistic evidence, culminating in a comprehensive conclusion about causality. Epidemiological evidence derived from population studies is categorized into four levels-high, moderate, limited, or insufficient-while mechanistic evidence, primarily from biological and clinical studies in animals and individuals, is classified as strong, intermediate, weak, or lacking. The committee then synthesizes these two types of evidence to draw a conclusion about the causal relationship, which can be described as "convincingly supports" ("evidence established" in the 2024 NASEM report), "favors acceptance," "favors rejection," or "inadequate to accept or reject." The CoVaSC has established an independent committee to conduct causality assessments using the weight-of-evidence framework, specifically for evaluating the causality of adverse events associated with COVID-19 vaccines. The aim of this study is to provide an overview of the weight-of-evidence framework and to detail the considerations involved in its practical application in the CoVaSC.
Assuntos
Vacinas contra COVID-19 , COVID-19 , SARS-CoV-2 , Humanos , Vacinas contra COVID-19/efeitos adversos , COVID-19/prevenção & controle , COVID-19/epidemiologia , SARS-CoV-2/imunologia , República da Coreia/epidemiologia , Causalidade , Estados UnidosRESUMO
PURPOSE: To develop and evaluate artificial intelligence (AI) algorithms for ultrasound (US) microflow imaging (MFI) in breast cancer diagnosis. MATERIALS AND METHODS: We retrospectively collected a dataset consisting of 516 breast lesions (364 benign and 152 malignant) in 471 women who underwent B-mode US and MFI. The internal dataset was split into training (n = 410) and test datasets (n = 106) for developing AI algorithms from deep convolutional neural networks from MFI. AI algorithms were trained to provide malignancy risk (0-100%). The developed AI algorithms were further validated with an independent external dataset of 264 lesions (229 benign and 35 malignant). The diagnostic performance of B-mode US, AI algorithms, or their combinations was evaluated by calculating the area under the receiver operating characteristic curve (AUROC). RESULTS: The AUROC of the developed three AI algorithms (0.955-0.966) was higher than that of B-mode US (0.842, P < 0.0001). The AUROC of the AI algorithms on the external validation dataset (0.892-0.920) was similar to that of the test dataset. Among the AI algorithms, no significant difference was found in all performance metrics combined with or without B-mode US. Combined B-mode US and AI algorithms had a higher AUROC (0.963-0.972) than that of B-mode US (P < 0.0001). Combining B-mode US and AI algorithms significantly decreased the false-positive rate of BI-RADS category 4A lesions from 87% to 13% (P < 0.0001). CONCLUSION: AI-based MFI diagnosed breast cancers with better performance than B-mode US, eliminating 74% of false-positive diagnoses in BI-RADS category 4A lesions.
Assuntos
Algoritmos , Inteligência Artificial , Neoplasias da Mama , Ultrassonografia Mamária , Humanos , Feminino , Neoplasias da Mama/diagnóstico por imagem , Estudos Retrospectivos , Ultrassonografia Mamária/métodos , Adulto , Pessoa de Meia-Idade , Idoso , Redes Neurais de Computação , Sensibilidade e Especificidade , Curva ROC , Mama/diagnóstico por imagemRESUMO
The performance of home care globally is significantly impacted by the political reforms in the public and private sectors. This research investigated the Australian contexts of home care quality and the use of "brokerage" during times of change. The research utilised a qualitative post-structural approach to gather data about home care service provision through conducting semi-structured interviews of 10 Australian home care business leaders. What emerged in the discourse was how central to everyday practices was the need for business leaders to network and 'dance a political tango' to ensure quality in service provision. Illuminated was how the leaders pushed back against governmental and economic structures by using models of brokerage to compensate for economic and staffing deficiencies. This is essential for the ongoing improvement and performance of home care in the Australian social arena of caring for our most vulnerable consumers.
Assuntos
Serviços de Assistência Domiciliar , Pesquisa Qualitativa , Humanos , Serviços de Assistência Domiciliar/tendências , Serviços de Assistência Domiciliar/normas , Austrália , Qualidade da Assistência à Saúde/normas , Entrevistas como Assunto/métodosRESUMO
Background: The importance of enhancing education to promote nursing students' patient safety competency is increasing. Hence, implementing diverse educational programs and assessing their outcomes is essential. Objectives: To examine the effects of flipped learning and gamification on nursing students' patient safety education. Design: A mixed-method design employing a quasi-experimental design with a pre-post control group design and qualitative thematic analysis. Methods: The study was conducted at a South Korean university in W City from September to December 2022. It included 55 s-year nursing students. The experimental group (n = 28) participated in a 30-h patient safety education course using flipped learning and gamification, whereas the control group (n = 27) received only written patient safety education materials. Learning motivation, collective efficacy, patient safety competency, and game evaluations were measured. Data were analyzed using the χ2 test, Fisher's exact test, t-test, repeated-measures multivariate analysis of covariance, repeated measure analysis of covariance, and generalized estimating equations. Self-reflection journals on game participation experiences were analyzed using qualitative thematic analysis. Results: Learning motivation scores did not differ significantly between groups for time, or interactions between groups and time, but collective efficacy and patient safety competency scores showed significant differences in the interactions between groups and time. The experimental group showed a high satisfaction score in game evaluation. Qualitative analyses were used to extract four themes-three positives: "fun and immersion differentiated from existing classes," "improved the learning outcomes and learning motivation," and "realized the value of collaboration and communication," and one negative: "feeling down due to unfamiliarity." Conclusions: This program creates positive learning experiences and enhances nursing students' collective efficacy and patient-safety competencies. It is expected to be utilized in various future nursing courses.
RESUMO
BACKGROUND: The current recommendation for the elderly is to receive both a single dose 23-valent pneumococcal polysaccharide vaccine (PPSV-23) and an annual inactivated influenza vaccine. There is a lack of post-marketing safety studies on concomitant vaccination using real-world data. We aimed to evaluate the safety of administering PPSV-23 and influenza vaccine concomitantly versus sequentially. METHODS: We performed a retrospective cohort study using a linked database that combines vaccination registry from the Korea Disease Control and Prevention Agency and claims data from the National Health Insurance Service. The study population included all those aged over 65 who received PPSV-23 at least once from Jan 1, 2016, to Dec 31, 2020. This study evaluated the 16 prespecified events of interest. Concomitant vaccination was defined as receiving both PPSV-23 and influenza vaccine on the same day. For sequential vaccination, we defined it as receiving influenza vaccination during the period from 30 to 365 days prior to the date of PPSV-23 injection. We performed 1:4 propensity score matching and estimated adjusted incidence rate ratio (aIRR) with a 95 % confidence interval (CI) using conditional Poisson regression. RESULTS: Of the 2,885,144 elderly patients who received PPSV-23 vaccination at least once from Jan 1, 2016, to Dec 31, 2020, a total 87,899 were included in the concomitant vaccination group and 1,200,091 were included in the sequential vaccination group. After adjusting for confounders, the concomitant group exhibited a significantly lower risk of allergic reactions (aIRR: 0.71, 95 % CI: 0.58-0.87), neuritis (aIRR: 0.72, 95 % CI: 0.57-0.91), and pneumonia (aIRR: 0.85, 95 % CI: 0.80-0.90), while demonstrating significantly higher risks of paralysis (aIRR: 1.63, 95 % CI: 1.05-2.52) compared to the sequential group. CONCLUSIONS: Concomitant administration of PPSV-23 and influenza vaccine in the elderly was not associated with a higher risk of most prespecified adverse events (AEs) compared to sequential vaccination. This study supports the safety of concomitant administration of PPSV-23 and influenza vaccine.
Assuntos
Vacinas contra Influenza , Influenza Humana , Vacinas Pneumocócicas , Humanos , Vacinas contra Influenza/efeitos adversos , Vacinas contra Influenza/administração & dosagem , Vacinas contra Influenza/imunologia , Vacinas Pneumocócicas/administração & dosagem , Vacinas Pneumocócicas/efeitos adversos , Vacinas Pneumocócicas/imunologia , Feminino , Idoso , Masculino , Estudos Retrospectivos , Idoso de 80 Anos ou mais , Influenza Humana/prevenção & controle , República da Coreia/epidemiologia , Vacinação/efeitos adversos , Vacinação/métodos , Infecções Pneumocócicas/prevenção & controleRESUMO
Versatile and efficient regulation of the mechanical properties of the extracellular matrix is crucial not only for understanding the dynamic changes in biological systems, but also for obtaining precise and effective cellular responses in drug testing. In this study, we developed a well plate-based hydrogel photo-crosslinking system to effectively control the mechanical properties of hydrogels and perform high-throughput assays. We improved cell biocompatibility by using gelatin methacryloyl (GelMA) with a visible light photo-crosslinking method. Multiple cell-laden GelMA hydrogels were simultaneously and uniformly created using multi-arrayed 520 nm light-emitting diodes in a well plate format. The elastic modulus of the hydrogels can be widely adjusted (0.5-30 kPa) using a photo-crosslinking system capable of independently controlling the light intensity or exposure time for multiple samples. We demonstrate the feasibility of our system by observing enhanced bone differentiation of human mesenchymal stem cells (hMSCs) cultured on stiffer hydrogels. Additionally, we observed that the osteogenic fate of hMSCs, affected by the different mechanical properties of the gel, was regulated by parathyroid hormone (PTH). Notably, in response to PTH, hMSCs in a high-stiffness microenvironment upregulate osteogenic differentiation while exhibiting increased proliferation in a low-stiffness microenvironment. Overall, the developed system enables the generation of multiple cell-laden three-dimensional cell culture models with diverse mechanical properties and holds significant potential for expansion into drug testing.
Assuntos
Hidrogéis , Hormônio Paratireóideo , Humanos , Hidrogéis/farmacologia , Osteogênese , Gelatina/farmacologia , Metacrilatos , Engenharia Tecidual/métodosRESUMO
BACKGROUND: The effectiveness of COVID-19 vaccines is generally reduced in cancer patients compared to the general population. However, there are only a few studies that compare the relative risk of breakthrough infections and severe COVID-19 outcomes in fully vaccinated cancer patients versus their unvaccinated counterparts. METHODS: To assess the effectiveness of COVID-19 vaccines in cancer patients, we employed (1) a self-controlled risk interval (SCRI) design, and (2) a retrospective matched cohort design. A SCRI design was used to compare the risk of breakthrough infection in vaccinated cancer patients during the period immediately following vaccination ("control window") and the period in which immunity is achieved ("exposure windows"). The retrospective matched cohort design was used to compare the risk of severe COVID-19 outcomes between vaccinated and unvaccinated cancer patients. For both studies, data were extracted from the Korea Disease Control and Prevention Agency-COVID-19-National Health Insurance Service cohort, including demographics, medical history, and vaccination records of all individuals confirmed with COVID-19. We used conditional Poisson regression to calculate the incidence rate ratio (IRR) for breakthrough infection and Cox regression to estimate the hazard ratio (HR) for severe outcomes. RESULTS: Of 14,448 cancer patients diagnosed with COVID-19 between October 2020 and December 2021, a total of 217 and 3996 cancer patients were included in the SCRI and cohort study respectively. While the risk of breakthrough infections, measured by the incidence rate in the control and exposure windows, did not show statistically significant difference in vaccinated cancer patients (IRR=0.88, 95% CI: 0.64-1.22), the risk of severe COVID-19 outcomes was significantly lower in vaccinated cancer patients compared to those unvaccinated (HR=0.27, 95% CI: 0.22-0.34). CONCLUSION: COVID-19 vaccines significantly reduce the risk of severe outcomes in cancer patients, though their efficacy against breakthrough infections is less evident.
Assuntos
COVID-19 , Neoplasias , Humanos , Vacinas contra COVID-19 , COVID-19/epidemiologia , COVID-19/prevenção & controle , Infecções Irruptivas , Estudos Retrospectivos , Estudos de Coortes , Vacinação , Neoplasias/complicaçõesRESUMO
Background: To improve the efficiency of neural development from human embryonic stem cells, human embryoid body (hEB) generation is vital through 3-dimensional formation. However, conventional approaches still have limitations: long-term cultivation and laborious steps for lineage determination. Methods: In this study, we controlled the size of hEBs for ectodermal lineage specification using cell-penetrating magnetic nanoparticles (MNPs), which resulted in reduced time required for initial neural induction. The magnetized cells were applied to concentrated magnetic force for magnet-derived multicellular organization. The uniformly sized hEBs were differentiated in neural induction medium (NIM) and suspended condition. This neurally induced MNP-hEBs were compared with other groups. Results: As a result, the uniformly sized MNP-hEBs in NIM showed significantly improved neural inductivity through morphological analysis and expression of neural markers. Signaling pathways of the accelerated neural induction were detected via expression of representative proteins; Wnt signaling, dopaminergic neuronal pathway, intercellular communications, and mechanotransduction. Consequently, we could shorten the time necessary for early neurogenesis, thereby enhancing the neural induction efficiency. Conclusion: Overall, this study suggests not only the importance of size regulation of hEBs at initial differentiation stage but also the efficacy of MNP-based neural induction method and stimulations for enhanced neural tissue regeneration.
RESUMO
Hydrogels are widely used as scaffold materials for constructingin vitrothree-dimensional microphysiological systems. However, their high sensitivity to various external cues hinders the development of hydrogel-laden, microscale, and high-throughput chips. Here, we have developed a long-term storable gel-laden chip composite built in a multi-well plate, which enablesin situcell encapsulation and facilitates high-throughput analysis. Through optimized chemical crosslinking and freeze-drying method (C/FD), we have achieved a high-quality of gel-laden chip composite with excellent transparency, uniform porosity, and appropriate swelling and mechanical characteristics. Besides collagen, decellularized extracellular matrix with tissue-specific biochemical compound has been applied as chip composite. As a ready-to-use platform,in situcell encapsulation within the gel has been achieved through capillary force generated during gel reswelling. The liver-mimetic chip composite, comprising HepG2 cells or primary hepatocytes, has demonstrated favorable hepatic functionality and high sensitivity in drug testing. The developed fabrication process with improved stability of gels and storability allows chip composites to be stored at a wide range of temperatures for up to 28 d without any deformation, demonstrating off-the-shelf products. Consequently, this provides an exceptionally simple and long-term storable platform that can be utilized for an efficient tissue-specific modeling and various biomedical applications.
Assuntos
Hidrogéis , Fígado , Humanos , Hidrogéis/química , Colágeno , Hepatócitos , Células Hep G2RESUMO
The effects of milling, washing, and cooking on etofenprox, flubendiamide, and tebufenozide levels in brown and polished rice were investigated by HPLC using a UV detector. The reduction rates of etofenprox, flubendiamide, and tebufenozide after milling were 68.74-93.16%, 64.49-90.25%, and 69.74-92.58%, respectively, 11.64-41.44%, 31.36-65.37%, and 31.61-73.79%, respectively, after washing brown rice, and 30.85-82.08%, 52.13-83.05%, and 43.04-83.89%, respectively, after washing polished rice. The residue levels of the three pesticides in brown rice decreased after electric and pressure cooking by 56.49 and 54.41%, 75.80 and 73.42%, and 70.01 and 71.27%, respectively, and the corresponding levels in polished rice decreased after electric and pressure cooking by 85.58 and 85.82%, 86.70 and 87.06%, and 89.89 and 89.68%, respectively. In conclusion, various processing methods decrease the residual levels of etofenprox, flubendiamide, and tebufenozide in rice.
RESUMO
PURPOSE: To investigate whether preoperative ultrasonographic (US) features of the index cancer and metastatic lymph nodes (LNs) are associated with level II LN metastasis in N1b papillary rmfthyroid carcinoma (PTC) patients. MATERIALS AND METHODS: We enrolled 517 patients (mean age, 42 [range, 6-80] years) who underwent total thyroidectomy and lateral compartment LN dissection between January 2009 and December 2015. We reviewed the clinicopathologic and US features of the index cancer and metastatic LNs in the lateral neck. Logistic regression analysis was performed to analyze features associated with level II LN metastasis. RESULTS: Among the patients, 196 (37.9%) had level II metastasis on final pathology. In the preoperative model, larger tumor size (odds ratios [ORs], 1.031; 95% confidence interval [CI]: 1.011-1.051, p = 0.002), nonparallel tumor shape (OR, 1.963; 95% CI: 1.322-2.915, p = 0.001), multilevel LN involvement (OR, 1.906; 95% CI: 1.242-2.925, p = 0.003), and level III involvement (OR, 1.867; 95% CI: 1.223-2.850, p = 0.004), were independently associated with level II LN metastasis. In the postoperative model, non-conventional pathology remained a significant predictor for level II LN metastasis (OR, 1.951; 95% CI: 1.121-3.396; p = 0.018), alongside the presence of extrathyroidal extension (OR, 1.867; 95% CI: 1.060-3.331; p = 0.031), and higher LN ratio (OR, 1.057; 95% CI: 1.039-1.076; p < 0.001). CONCLUSIONS: Preoperative US features of the index tumor and LN may be helpful in guiding surgery in N1b PTC. These findings could enhance preoperative planning and decision-making, potentially reducing surgical morbidities by identifying those at higher risk of level II LN metastasis and tailoring surgical approaches accordingly.
RESUMO
A web-based clinical simulation program, known as FIRST2ACT (Feedback Incorporating Review and Simulation Techniques to Act on Clinical Trends), was designed to increase the efficacy of clinicians' actions in the recognition and immediate response to a patient's deterioration. This study, which was nested in a larger mixed method project, used ten focus groups (n = 65) of graduate, enrolled, registered nurses, associate nurse unit managers, and general managers/educators/coordinators from four different institutions to investigate whether nurses felt their practice was influenced by participating in either a face-to-face or web-based simulation educational programme about patient deterioration. The results indicate that individuals who were less "tech-savvy" appreciated the flexibility of web-based learning, which increased their confidence. Face-to-face students appreciated self-reflection through performance evaluation. While face-to-face simulations were unable to completely duplicate symptoms, they showed nurses' adaptability. Both interventions enhanced clinical practice by improving documentation and replies while also boosting confidence and competence. Web learners initially experienced tech-related anxiety, which gradually subsided, demonstrating healthcare professionals' resilience to new learning approaches. Overall, the study highlighted the advantages and challenges of web-based and face-to-face education in clinical practice, emphasising the importance of adaptability and reflective learning for healthcare professionals. Further exploration of specific topics is required to improve practice, encourage knowledge sharing among colleagues, and improve early detection of patient deterioration.
RESUMO
Bladder cancer is the most common urological malignancy worldwide, and its high recurrence rate leads to poor survival outcomes. The effect of anticancer drug treatment varies significantly depending on individual patients and the extent of drug resistance. In this study, we developed a validation system based on an organ-on-a-chip integrated with artificial intelligence technologies to predict resistance to anticancer drugs in bladder cancer. As a proof-of-concept, we utilized the gemcitabine-resistant bladder cancer cell line T24 with four distinct levels of drug resistance (parental, early, intermediate, and late). These cells were co-cultured with endothelial cells in a 3D microfluidic chip. A dataset comprising 2,674 cell images from the chips was analyzed using a convolutional neural network (CNN) to distinguish the extent of drug resistance among the four cell groups. The CNN achieved 95.2% accuracy upon employing data augmentation and a step decay learning rate with an initial value of 0.001. The average diagnostic sensitivity and specificity were 90.5% and 96.8%, respectively, and all area under the curve (AUC) values were over 0.988. Our proposed method demonstrated excellent performance in accurately identifying the extent of drug resistance, which can assist in the prediction of drug responses and in determining the appropriate treatment for bladder cancer patients.