Integrating predictive coding and a user-centric interface for enhanced auditing and quality in cancer registry data.

Data curation for a hospital-based cancer registry heavily relies on the labor-intensive manual abstraction process by cancer registrars to identify cancer-related information from free-text electronic health records. To streamline this process, a natural language processing system incorporating a hybrid of deep learning-based and rule-based approaches for identifying lung cancer registry-related concepts, along with a symbolic expert system that generates registry coding based on weighted rules, was developed. The system is integrated with the hospital information system at a medical center to provide cancer registrars with a patient journey visualization platform. The embedded system offers a comprehensive view of patient reports annotated with significant registry concepts to facilitate the manual coding process and elevate overall quality. Extensive evaluations, including comparisons with state-of-the-art methods, were conducted using a lung cancer dataset comprising 1428 patients from the medical center. The experimental results illustrate the effectiveness of the developed system, consistently achieving F1-scores of 0.85 and 1.00 across 30 coding items. Registrar feedback highlights the system's reliability as a tool for assisting and auditing the abstraction. By presenting key registry items along the timeline of a patient's reports with accurate code predictions, the system improves the quality of registrar outcomes and reduces the labor resources and time required for data abstraction. Our study highlights advancements in cancer registry coding practices, demonstrating that the proposed hybrid weighted neural-symbolic cancer registry system is reliable and efficient for assisting cancer registrars in the coding workflow and contributing to clinical outcomes.

Predicting Lung Cancer Survival to the Future: Population-Based Cancer Survival Modeling Study.

BACKGROUND: Lung cancer remains the leading cause of cancer-related mortality globally, with late diagnoses often resulting in poor prognosis. In response, the Lung Ambition Alliance aims to double the 5-year survival rate by 2025. OBJECTIVE: Using the Taiwan Cancer Registry, this study uses the survivorship-period-cohort model to assess the feasibility of achieving this goal by predicting future survival rates of patients with lung cancer in Taiwan. METHODS: This retrospective study analyzed data from 205,104 patients with lung cancer registered between 1997 and 2018. Survival rates were calculated using the survivorship-period-cohort model, focusing on 1-year interval survival rates and extrapolating to predict 5-year outcomes for diagnoses up to 2020, as viewed from 2025. Model validation involved comparing predicted rates with actual data using symmetric mean absolute percentage error. RESULTS: The study identified notable improvements in survival rates beginning in 2004, with the predicted 5-year survival rate for 2020 reaching 38.7%, marking a considerable increase from the most recent available data of 23.8% for patients diagnosed in 2013. Subgroup analysis revealed varied survival improvements across different demographics and histological types. Predictions based on current trends indicate that achieving the Lung Ambition Alliance's goal could be within reach. CONCLUSIONS: The analysis demonstrates notable improvements in lung cancer survival rates in Taiwan, driven by the adoption of low-dose computed tomography screening, alongside advances in diagnostic technologies and treatment strategies. While the ambitious target set by the Lung Ambition Alliance appears achievable, ongoing advancements in medical technology and health policies will be crucial. The study underscores the potential impact of continued enhancements in lung cancer management and the importance of strategic health interventions to further improve survival outcomes.

Laser beam homogenization based on a multifocal liquid crystal microlens array.

A novel, to the best of our knowledge, tunable multifocal liquid crystal microlens array (TMLCMA) was fabricated with a triple-electrode structure consisting of a large-hole, a small-hole array, and planar electrodes. The electro-optical performances of the TMLCMA are characterized, demonstrating the monofocal convex, multifocal convex, and multifocal concave functions when the TMLCMA is manipulated with various driving schemes. Furthermore, the homogenization of a laser beam is realized using the fabricated TMLCMA. The multifocal convex and multifocal concave functions of the TMLCMA successfully suppress the lattice phenomenon caused by the monofocal microlens array, homogenize the Gaussian beam to a flattop intensity distribution, and broaden the beam size.