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.

Handheld Biosensor System Based on a Gradient Grating Period Guided-Mode Resonance Device.

Handheld biosensors have attracted substantial attention for numerous applications, including disease diagnosis, drug dosage monitoring, and environmental sensing. This study presents a novel handheld biosensor based on a gradient grating period guided-mode resonance (GGP-GMR) sensor. Unlike conventional GMR sensors, the proposed sensor's grating period varies along the device length; hence, the resonant wavelength varies linearly along the device length. If a GGP-GMR sensor is illuminated with a narrow band of light at normal incidence, the light resonates and reflects at a specific period but transmits at other periods; this can be observed as a dark band by using a complementary metal oxide semiconductor (CMOS) underneath the sensor. The concentration of a target analyte can be determined by monitoring the shift of this dark band. We designed and fabricated a handheld device incorporating a light-emitting diode (LED) light source, the necessary optics, an optofluidic chip with an embedded GGP-GMR sensor, and a CMOS. LEDs with different beam angles and bandpass filters with different full width at half maximum values were investigated to optimize the dark band quality and improve the accuracy of the subsequent image analysis. Substrate materials with different refractive indices and waveguide thicknesses were also investigated to maximize the GGP-GMR sensor's figure of merit. Experiments were performed to validate the proposed handheld biosensor, which achieved a limit of detection (LOD) of 1.09 × 10-3 RIU for bulk solution measurement. The sensor's performance in the multiplexed detection of albumin and creatinine solutions at concentrations of 0-500 µg/mL and 0-10 mg/mL, respectively, was investigated; the corresponding LODs were 0.66 and 0.61 µg/mL.

Developing an App by Exploiting Web-Based Mobile Technology to Inspect Controlled Substances in Patient Care Units.

We selected iOS in this study as the App operation system, Objective-C as the programming language, and Oracle as the database to develop an App to inspect controlled substances in patient care units. Using a web-enabled smartphone, pharmacist inspection can be performed on site and the inspection result can be directly recorded into HIS through the Internet, so human error of data translation can be minimized and the work efficiency and data processing can be improved. This system not only is fast and convenient compared to the conventional paperwork, but also provides data security and accuracy. In addition, there are several features to increase inspecting quality: (1) accuracy of drug appearance, (2) foolproof mechanism to avoid input errors or miss, (3) automatic data conversion without human judgments, (4) online alarm of expiry date, and (5) instant inspection result to show not meted items. This study has successfully turned paper-based medication inspection into inspection using a web-based mobile device.