Conectar
Although lung cancer remains the leading cause of cancer deaths in the US, recent advances in early detection and treatment have led to improvements in survival. However, there is a considerable risk of recurrence or second primary lung cancer (SPLC) following curative-intent treatment in patients with early-stage non-small cell lung cancer (NSCLC). Professional societies recommend routine surveillance with CT to optimise the detection of potential recurrence and SPLC at a localised stage. However, no definitive evidence demonstrates the effect of imaging surveillance on survival in patients with NSCLC. To close these research gaps, the Advancing Precision Lung Cancer Surveillance and Outcomes in Diverse Populations (PLuS2) study will leverage real-world electronic health records (EHRs) data to evaluate surveillance outcomes among patients with and without guideline-adherent surveillance. The overarching goal of the PLuS2 study is to assess the long-term effectiveness of surveillance strategies in real-world settings.
PLuS2 is an observational study designed to assemble a cohort of patients with incident pathologically confirmed stage I/II/IIIA NSCLC who have completed curative-intent therapy. Patients undergoing imaging surveillance will be followed from 2012 to 2026 by linking EHRs with tumour registry data in the OneFlorida+ Clinical Research Consortium. Data will be consolidated into a unified repository to achieve three primary aims: (1) Examine the utilisation and determinants of CT imaging surveillance by race/ethnicity and socioeconomic status, (2) Compare clinical endpoints, including recurrence, SPLCs and survival of patients who undergo semiannual versus annual CT imaging and (3) Use the observational data in conjunction with validated microsimulation models to simulate imaging surveillance outcomes within the US population. To our knowledge, this study represents the first attempt to integrate real-world data and microsimulation models to assess the long-term impact and effectiveness of imaging surveillance strategies.
This study involves human participants and was approved by the University of Florida Institutional Review Board (IRB), University of Florida IRB 01, under approval number IRB202300782. The results will be disseminated through publications and presentations at national and international conferences. Safety considerations encompass ensuring the confidentiality of patient information. All disseminated data will be de-identified and summarised.
First, to investigate residential aged care staff's knowledge and understanding of residents after viewing their digital life story. Second, to examine the stability of this knowledge and understanding. Third, to explore staff's self-reported care practices following digital life story viewing.
Australian aged care quality standards include person-centred care practices, although opportunity for residents' identity expression can be limited by the facility environment. Staff cannot implement such practices without first understanding residents' history, preferences, and values.
The study used a convergent mixed methods design.
Residential aged care staff (n = 61) viewed a resident's digital life story and completed a measure of their knowledge and understanding of the resident at pre-test, post-test, and follow-up. At post-test and follow-up, staff were also asked to indicate if viewing the story had improved their interactions and care practices with the resident and to describe changes in their practice. Pre-test, post-test and follow-up scores of the measure were compared using a repeated measures analysis of variance with post hoc comparisons. Qualitative responses were analysed using thematic analysis.
Scores at post-test and follow-up were significantly higher than at pre-test, showing a stable improvement in knowledge and understanding of residents. Staff responses indicated their knowledge and understanding of residents' life story enhanced their care towards the residents.
Watching digital life stories was associated with stable improvements in staff's knowledge of residents, with staff feeling better equipped to personalise care practices.
Digital life stories about aged-care residents may support staff's improved knowledge and understanding of their care-recipients. With such understanding, staff are more equipped to implement person-centred care practices by Australian aged care quality standards.
The study adhered to guidelines for Revised Standards for Quality Improvement Reporting Excellence (SQUIRE 2.0).
No patient or public contribution.
Common goals for procedural sedation are to control pain and ensure the patient is not moving to an extent that is impeding safe progress or completion of the procedure. Clinicians perform regular assessments of the adequacy of procedural sedation in accordance with these goals to inform their decision-making around sedation titration and also for documentation of the care provided. Natural language processing could be applied to real-time transcriptions of audio recordings made during procedures in order to classify sedation states that involve movement and pain, which could then be integrated into clinical documentation systems. The aim of this study was to determine whether natural language processing algorithms will work with sufficient accuracy to detect sedation states during procedural sedation.
A prospective observational study was conducted.
Audio recordings from consenting participants undergoing elective procedures performed in the interventional radiology suite at a large academic hospital were transcribed using an automated speech recognition model. Sentences of transcribed text were used to train and evaluate several different NLP pipelines for a text classification task. The NLP pipelines we evaluated included a simple Bag-of-Words (BOW) model, an ensemble architecture combining a linear BOW model and a “token-to-vector” (Tok2Vec) component, and a transformer-based architecture using the RoBERTa pre-trained model.
A total of 15,936 sentences from transcriptions of 82 procedures was included in the analysis. The RoBERTa model achieved the highest performance among the three models with an area under the ROC curve (AUC-ROC) of 0.97, an F1 score of 0.87, a precision of 0.86, and a recall of 0.89. The Ensemble model showed a similarly high AUC-ROC of 0.96, but lower F1 score of 0.79, precision of 0.83, and recall of 0.77. The BOW approach achieved an AUC-ROC of 0.97 and the F1 score was 0.7, precision was 0.83 and recall was 0.66.
The transformer-based architecture using the RoBERTa pre-trained model achieved the best classification performance. Further research is required to confirm the that this natural language processing pipeline can accurately perform text classifications with real-time audio data to allow for automated sedation state assessments.
Automating sedation state assessments using natural language processing pipelines would allow for more timely documentation of the care received by sedated patients, and, at the same time, decrease documentation burden for clinicians. Downstream applications can also be generated from the classifications, including for example real-time visualizations of sedation state, which may facilitate improved communication of the adequacy of the sedation between clinicians, who may be performing supervision remotely. Also, accumulation of sedation state assessments from multiple procedures may reveal insights into the efficacy of particular sedative medications or identify procedures where the current approach for sedation and analgesia is not optimal (i.e. a significant amount of time spent in “pain” or “movement” sedation states).
FreshRSS 