Search NASA⌕ Search

SEARCH · Search NASA

Results for “Automated medical encoding”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

5 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Deformable phrase level attention: A flexible approach for improving AI based medical coding

Objective: Improving the AI-driven automated medical encoding of clinical text plays a vital role in gathering information on the occurrence of diseases to improve population-level health. This work presents a novel attention mechanism designed to enhance text classification models and ensure appropriate classification of medical concepts in unstructured electronic health records. Materials and Methods: We developed a deformable, phrase-level attention mechanism to identify important lexical word-level and contextual phrase-level information from clinical text documents. We evaluated conventional and transformer-based deep learning models that we extended with our attention mechanism on the extraction of critical cancer information (e.g., site, subsite, laterality, histology, behavior) from 629,908 electronic pathology reports and on the automated medical encoding of 52,722 hospital discharge summaries. Results: Transformer-based models with the deformable, phrase-level attention mechanism achieved the best performance on the extraction of critical cancer information from pathology reports. Conventional- and transformer-based models show similar or better performance than their baseline counterparts on the automated medical encoding of clinical documents. Discussion: The addition of phrase-level information allowed models extended with our proposed method to outperform standard word-level attention. Our method showed favorable properties for the real-world application in terms of model robustness and phenotyping. These results indicate that our method is promising for automated data harmonization for common data models. Conclusion: This work proposes a novel deformable, phrase-level attention mechanism that enhances text classification models in the extraction of medical concepts from clinical text documents. We demonstrate strong performances on two clinical text datasets and showcase real-world deployability of our method.

Automated medical encoding↗
NASA NTRS2006

Medical Signal-Conditioning and Data-Interface System

A general-purpose portable, wearable electronic signal-conditioning and data-interface system is being developed for medical applications. The system can acquire multiple physiological signals (e.g., electrocardiographic, electroencephalographic, and electromyographic signals) from sensors on the wearer s body, digitize those signals that are received in analog form, preprocess the resulting data, and transmit the data to one or more remote location(s) via a radiocommunication link and/or the Internet. The system includes a computer running data-object-oriented software that can be programmed to configure the system to accept almost any analog or digital input signals from medical devices. The computing hardware and software implement a general-purpose data-routing-and-encapsulation architecture that supports tagging of input data and routing the data in a standardized way through the Internet and other modern packet-switching networks to one or more computer(s) for review by physicians. The architecture supports multiple-site buffering of data for redundancy and reliability, and supports both real-time and slower-than-real-time collection, routing, and viewing of signal data. Routing and viewing stations support insertion of automated analysis routines to aid in encoding, analysis, viewing, and diagnosis.

Braun, Jeffrey↗
NASA NTRS2006

NASA Tech Briefs, March 2006

Topics covered include: Medical Signal-Conditioning and Data-Interface System; Instruments for Reading Direct-Marked Data-Matrix Symbols; Processing EOS MLS Level-2 Data; Ground Processing of Data From the Mars Exploration Rovers; Estimating Total Electron Content Using 1,000+ GPS Receivers; NASA Solar Array Demonstrates Commercial Potential; Improved Control of Charging Voltage for Li-Ion Battery; Programmable Pulse-Position-Modulation Encoder; Wavelength-Agile External-Cavity Diode Laser for DWDM; Pattern-Recognition Processor Using Holographic Photopolymer; Submicrosecond Power-Switching Test Circuit; Three-Function Logic Gate Controlled by Analog Voltage; Integrated System for Autonomous Science; Montage Version 3.0; Utilizing AI in Temporal, Spatial, and Resource Scheduling; Satellite Image Mosaic Engine; Architecture for Control of the K9 Rover; HFGMC Enhancement of MAC/GMC; Automated Activation and Deactivation of a System Under Test; Cleaning Carbon Nanotubes by Use of Mild Oxygen Plasmas; Generating Aromatics From CO2 on Mars or Natural Gas on Earth; Attaching Thermocouples by Peening or Crimping; Heat Treatment of Friction-Stir-Welded 7050 Aluminum Plates; Generating Breathable Air Through Dissociation of N2O; High-Performance Scanning Acousto-Ultrasonic System; Correction for Thermal EMFs in Thermocouple Feedthroughs; Using Quasiparticle Poisoning To Detect Photons; Estimating Resolution Lengths of Hybrid Turbulence Models; Education and Training Module in Alertness Management; Cargo-Positioning System for Next-Generation Spacecraft; Micro-Imagers for Spaceborne Cell-Growth Experiments; Holographic Solar Photon Thrusters; Plasma-Based Detector of Outer-Space Dust Particles; and Generation of Data-Rate Profiles of Ka-Band Deep-Space Links.

Source record↗
DOE OSTI2024

Automating the Analysis of Large Language Models Responses through Zero-Shot Question Answering

Recent advancements in Large Language Models (LLMs) have shown significant potential in various applications, yet their evaluation, particularly in zero-shot question answering scenarios, remains a challenging task. In this study, our objective was to explore precision metrics for Large Language Models (LLM) and design and implement a software pipeline to automatically evaluate LLMs' outputs under zero-shot question answering. Zero-shot question answering involves a model providing answers to questions about topics it hasn't seen during training. It leverages the principles of zero-shot learning by relying on semantic understanding and generalization from related knowledge. The data used was metadata from medical databases on congenital heart disease. We explored eleven LLM metrics and selected three for our evaluation: BLEU, BERTScore, and MoverScore. BLEU calculates a score based on the overlap of n-grams (contiguous sequences of n items, typically words) between the machine-generated translation and the reference translations. Higher BLEU scores indicate better correspondence between the machine-generated and human-generated translations. BERTScore is a metric used to evaluate the quality of machine-generated text by measuring the similarity of token embeddings produced by BERT (Bidirectional Encoder Representations from Transformers) between the generated text and reference text. MoverScore is a metric that quantifies the dissimilarity between the distributions of word embeddings from machine-generated text and reference text, emphasizing semantic similarity over exact token overlap. We also introduced HBKI, a composite metric summarizing these approaches. We tested five models —GPT-3, Llama-2, Gemini 1.5 Pro, Solar 10.7B, and Mixtral-8x7b. Our software pipeline, designed and implemented using Object-Oriented Programming principles, allows users to customize the selection and extraction of features for topics of interest in their own research. Our results show that MoverScore delivered the most precise evaluation of the LLM's outputs, while Mixtral-8x7b achieved the best overall performance in extracting metadata from the databases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Embedded EPICS server for PowerPMAC motion controllers

An embedded server layer of Experimental Physics and Industrial Control System (EPICS) for PowerPMAC motion controllers has been developed and deployed at two undulator beamlines of the National Institute of General Medical Sciences and the National Cancer Institute (GM/CA) Structural Biology Facility at the Advanced Photon Source (APS). This compact, open source solution makes the power and versatility of PowerPMAC motion controls directly accessible to distributed EPICS clients. At GM/CA the system controls about 200 servo and stepper motors — both encoded and unencoded — and multiple digital and analog I/O accessories. The server stack comprises two sublayers: a lower-level driver and database that communicates directly with PowerPMAC, and a facility-specific soft sublayer built on top. The paper describes installing EPICS on PowerPMAC, the implementation of both layers and client examples, including on-the-fly scanning.

EPICS↗