FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366993910> ?p ?o ?g. }

• W4366993910 endingPage "1065" @default.
• W4366993910 startingPage "1064" @default.
• W4366993910 abstract "Dear Editor, The study ‘Preoperative data-based deep learning model for predicting postoperative survival in pancreatic cancer patients’ presents an interesting study on using a convolutional neural network to predict postoperative survival in patients with pancreatic ductal adenocarcinoma (PDAC)1. The study was based on preoperative clinical data and aimed to predict the probability of long-term survival after surgery. The authors claimed that the convolutional neural network model achieved high accuracy in predicting survival outcomes and performed better than other traditional prognostic models. However, there are several issues in this study that should be addressed. First, the study1 had a relatively small sample size (229 patients in the training data set and only 53 in the test data set), which may have limited the generalizability of the findings. In addition, the study only focused on patients who underwent surgical resection, which may not be representative of all pancreatic cancer patients. For example, it needs to be mentioned that the conclusions of this study do not apply to PDAC patients who missed the timing of surgery or received conservative treatment. Second, this article does not provide detailed information on the specific clinical data and features that were used to train the model. The only information we have learned is that the model established in this study is useful for predicting the prognosis of PDAC patients. However, it is unclear what variables were considered in the model and how they were processed and analyzed to produce the prediction. This lack of transparency makes it difficult for other researchers to replicate the study, compare their results with those of the current study, and assess the generalizability of the model to different patient populations. Without knowing the features used in the model, it is also challenging to evaluate the validity and clinical significance of the results. The potential clinical impact of the model would depend on the relevance of the features to patient outcomes as well as the model’s performance in predicting survival. Third, the information about specific drugs or chemoradiation therapy (CRT) strategies used in the study population is lacking. Given the importance of chemotherapy and radiation therapy in the management of pancreatic cancer, it is important to consider their effects on patient outcomes. A study2 involving 240 PDAC patients found that patients treated with neoadjuvant therapy had better overall survival and a lower rate of lymph node metastases compared with those who did not receive neoadjuvant therapy. Another study3 demonstrated that preoperative CRT was associated with less margin and lymph node positivity and reduced locoregional recurrence, and the benefits on overall survival were similar to those of patients receiving preoperative chemotherapy. The above evidence undoubtedly shows that drug or chemoradiotherapy treatment strategies are related to the prognosis of PDAC patients. Thus, it is important to examine the relationship between specific drugs/CRT and neoadjuvant therapy and patient survival. This information is crucial for the development of predictive models that can accurately capture the complex interactions between treatment and survival. Ethical approval Not applicable. Source of funding None. Author contribution M.Z. design and write this letter. Conflict of interest disclosure None. Research registration unique identifying number (UIN) Name of the registry: not applicable. Unique identifying number or registration ID: not applicable. Hyperlink to your specific registration (must be publicly accessible and will be checked): not applicable. Guarantor Miaoying Zhao. Provenance and peer review Commentary, internally reviewed" @default.
• W4366993910 created "2023-04-27" @default.
• W4366993910 creator A5090611329 @default.
• W4366993910 date "2023-03-14" @default.
• W4366993910 modified "2023-09-26" @default.
• W4366993910 title "Letter to the editor regarding ‘Preoperative data-based deep learning model for predicting postoperative survival in pancreatic cancer patients’" @default.
• W4366993910 cites W1544019504 @default.
• W4366993910 cites W2913927793 @default.
• W4366993910 cites W4293483498 @default.
• W4366993910 doi "https://doi.org/10.1097/js9.0000000000000306" @default.
• W4366993910 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37097622" @default.
• W4366993910 hasPublicationYear "2023" @default.
• W4366993910 type Work @default.
• W4366993910 citedByCount "0" @default.
• W4366993910 crossrefType "journal-article" @default.
• W4366993910 hasAuthorship W4366993910A5090611329 @default.
• W4366993910 hasBestOaLocation W43669939101 @default.
• W4366993910 hasConcept C105795698 @default.
• W4366993910 hasConcept C121608353 @default.
• W4366993910 hasConcept C126322002 @default.
• W4366993910 hasConcept C143998085 @default.
• W4366993910 hasConcept C27158222 @default.
• W4366993910 hasConcept C2780210213 @default.
• W4366993910 hasConcept C2992026798 @default.
• W4366993910 hasConcept C2993277928 @default.
• W4366993910 hasConcept C3019894029 @default.
• W4366993910 hasConcept C33923547 @default.
• W4366993910 hasConcept C71924100 @default.
• W4366993910 hasConceptScore W4366993910C105795698 @default.
• W4366993910 hasConceptScore W4366993910C121608353 @default.
• W4366993910 hasConceptScore W4366993910C126322002 @default.
• W4366993910 hasConceptScore W4366993910C143998085 @default.
• W4366993910 hasConceptScore W4366993910C27158222 @default.
• W4366993910 hasConceptScore W4366993910C2780210213 @default.
• W4366993910 hasConceptScore W4366993910C2992026798 @default.
• W4366993910 hasConceptScore W4366993910C2993277928 @default.
• W4366993910 hasConceptScore W4366993910C3019894029 @default.
• W4366993910 hasConceptScore W4366993910C33923547 @default.
• W4366993910 hasConceptScore W4366993910C71924100 @default.
• W4366993910 hasIssue "4" @default.
• W4366993910 hasLocation W43669939101 @default.
• W4366993910 hasLocation W43669939102 @default.
• W4366993910 hasLocation W43669939103 @default.
• W4366993910 hasLocation W43669939104 @default.
• W4366993910 hasOpenAccess W4366993910 @default.
• W4366993910 hasPrimaryLocation W43669939101 @default.
• W4366993910 hasRelatedWork W2080742495 @default.
• W4366993910 hasRelatedWork W2207015643 @default.
• W4366993910 hasRelatedWork W2423915749 @default.
• W4366993910 hasRelatedWork W2512645023 @default.
• W4366993910 hasRelatedWork W2595377073 @default.
• W4366993910 hasRelatedWork W3104966608 @default.
• W4366993910 hasRelatedWork W3129048113 @default.
• W4366993910 hasRelatedWork W3154040450 @default.
• W4366993910 hasRelatedWork W4288497676 @default.
• W4366993910 hasRelatedWork W4381233175 @default.
• W4366993910 hasVolume "109" @default.
• W4366993910 isParatext "false" @default.
• W4366993910 isRetracted "false" @default.
• W4366993910 workType "letter" @default.