Background In different cancer entities, several studies have shown the adverse effects of cancer on mental health, psychological well-being and the increased risk of high emotional distress in cancer patients. This study aims to analyze psychosocial distress levels and their relationship between sociodemographic parameters and selected items on the Distress Thermometer (DT) Problem List in head and neck squamous cell carcinoma (HNSCC) patients. Patients and methods We assessed a total of 120 HNSCC patients using the Distress Thermometer (DT) Problem List. Distress scores (DTS) of 90 patients were available. A DTS of ≥ 5 on the visual analogue scale represents clinically relevant distress. Data analysis consisted of descriptive statistics, comparison of mean values for different DTS subcategories and correlation between DTS scores and parameters of tumor classification, sociodemographic variables and selected problems. Results Distress was present in 57.7% of the sample, with a total of 52 patients with a DTS ≥ 5. The mean DTS was 4.7 (SD 2.4). Patients with newly diagnosed HNSCC had significantly higher DTS. Distress levels were significantly associated with sadness, general worries, anxiety, nervousness, sleeping disorders, mouth sores and fever. Out of the total sample, 6 patients and out of these 6 individuals, 5 patients with a DTS ≥ 5 requested referrals to psycho-oncological service. Conclusion High distress levels were common in HNSCC patients but only few patients desired psycho-oncological care. Addressing patients’ supportive care needs in routine clinical practice is essential to meet unmet needs of HNSCC patients and thus improve cancer care.
Introduction: Frailty represents a complex geriatric syndrome associated with elevated rates of postoperative complications as shown for several malignant entities, including head and neck cancer. A specific screening instrument to assess frailty in head and neck patients does not exist. Both the FRAIL Scale and the G8 questionnaire are well-established and easy to use as screening tools. The present study’s aim was to assess the potential of frailty screening to predict postoperative complications in head and neck patients prior to surgery. Patients and methods: We recorded demographic data, pre-existing medical conditions and clinical characteristics in a prospective cohort of 104 head and neck cancer patients undergoing major head and neck surgery and assessed frailty prospectively on the day of admission utilizing the G8 questionnaire and the FRAIL Scale. We analyzed the link between occurrence of postoperative complications up to the twenty-first postoperative day and age, frailty and other covariates using χ2 tests and receiver operating characteristic (ROC) curves. Results: There was no significant correlation between patients’ pre-existing medical conditions and postoperative complications. Whereas chronological age alone did not predict the occurrence of postoperative complications, frailty posed the highest risk for complications. Frailty according to either the G8 questionnaire or the FRAIL Scale predicted occurrence of complications with an area under the curve (AUC) of 0.64 (p = 0.018) and 0.62 (p = 0.039) and severe complications with an AUC of 0.72 (p = 0.014) and 0.69 (p=0.031), respectively. Neither frailty score correlated with age or with each other. Conclusion: Prospective screening using the FRAIL Scale or the G8 questionnaire reliably detected frailty in our sample group. Frailty is linked to increased risk of postoperative complications. The correct prediction of severe postoperative complications as shown identifies vulnerable cases and triggers awareness of potential complications. Anticipating risk allows for a more comprehensive view of the patient and triggers decision making towards risk adjustment, and therefore a selective view of alternative treatment modalities.
The documentation of a surgical procedure remains a time-consuming task that surgeons must incorporate into their daily routine. However, since a surgical report should be produced immediately after the operation with all impressions of the procedure in mind, a means of automation assistance should be provided. We, therefore, propose a method that generates surgical reports based on keywords stated during the procedure. Our report generation is based on a sequence-tosequence model that is trained on sentence pairs of two consecutive sentences in a surgical report. The known sentence is augmented with a keyword based on the following surgical action to be documented and is then passed into a language model to generate the next sentence. In this way, the complexity of predicting a vast number of possible surgical report phrasings is reduced to a next sentence prediction task. For the language model, an encoder-decoder structure was used with bidirectional 2-layer Long-Short Term Memory (LSTM) units for both components and an attention layer between input and output sentences. The training data consisted of 50 ear-,nose- and throat surgery (ENT) reports with 1500 sentences. The model training was performed in a k-fold cross-validation study with k = 10 and cross-entropy loss as the objective function. The generated reports were investigated using NIST, ROUGE, and METEOR metrics. Additionally, three medical experts identified the report content regarding plausibility and text errors. The trained models reached an accuracy of 0.82 for the next sentence predictions. The generated reports show consistent sentence structures and keyword correspondence for about 70 % of provided keyword sequences. The NIST, ROUGE, and METEOR metrics reached 0.65, 0.71, and 0.64, respectively. The model underperformed for not yet known keyword sequences and shows signs of overfitting when keyword sequences deviate from the baseline of the training set. Our approach for the keyword-augmented generation of surgical reports shows the potential of reducing the text generation complexity by providing a sequence of anchor words. However, the automated generation of surgical reports remains a difficult task due to individual report phrasings and the high variance in keyword sequences.
Introduction Surgical reports are usually written after a procedure and must often be reproduced from memory. Thus, this is an error-prone, and time-consuming task which increases the workload of physicians. In this proof-of-concept study, we developed and evaluated a software tool using Artificial Intelligence (AI) for semi-automatic intraoperative generation of surgical reports for functional endoscopic sinus surgery (FESS). Materials and methods A vocabulary of keywords for developing a neural language model was created. With an encoder-decoder-architecture, artificially coherent sentence structures, as they would be expected in general operation reports, were generated. A first set of 48 conventional operation reports were used for model training. After training, the reports were generated again and compared to those before training. Established metrics were used to measure optimization of the model objectively. A cohort of 16 physicians corrected and evaluated three randomly selected, generated reports in four categories: “quality of the generated operation reports,” “time-saving,” “clinical benefits” and “comparison with the conventional reports.” The corrections of the generated reports were counted and categorized. Results Objective parameters showed improvement in performance after training the language model (p < 0.001). 27.78% estimated a timesaving of 1–15 and 61.11% of 16–30 min per day. 66.66% claimed to see a clinical benefit and 61.11% a relevant workload reduction. Similarity in content between generated and conventional reports was seen by 33.33%, similarity in form by 27.78%. 66.67% would use this tool in the future. An average of 23.25 ± 12.5 corrections was needed for a subjectively appropriate surgery report. Conclusion The results indicate existing limitations of applying deep learning to text generation of operation reports and show a high acceptance by the physicians. By taking over this time-consuming task, the tool could reduce workload, optimize clinical workflows and improve the quality of patient care. Further training of the language model is needed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.