Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI-Driven Decision Support in Oncology: Evaluating Data Readiness for Skin Cancer Treatment

Joscha Grüger, Tobias Geyer, Tobias Brix, Michael Storck, Sonja Leson, Laura Bley, Carsten Weishaupt, Ralph Bergmann, Stephan A. Braun

TL;DR

The paper addresses the readiness of clinical data to support AI-driven decision support in oncology, focusing on skin cancer treatment. It introduces a data-centric AI-readiness framework and applies a six-step methodology at the Skin Tumor Center of the University Hospital Münster to assess data sources, extractability, and quality. The study identifies 41 decision-relevant data points, with substantial portions residing in unstructured text and cancer registries, revealing substantial barriers to real-world AI CDSS deployment. It emphasizes the need for standardized, comprehensive data documentation—including social and patient-centered factors—and outlines future work to expand datasets and determine sample sizes for an analogy-based CDSS. Overall, the work highlights data quality and availability as pivotal for effective AI-enhanced oncologic decision-making and provides a practical roadmap for data preparation in this domain.

Abstract

This research focuses on evaluating and enhancing data readiness for the development of an Artificial Intelligence (AI)-based Clinical Decision Support System (CDSS) in the context of skin cancer treatment. The study, conducted at the Skin Tumor Center of the University Hospital Münster, delves into the essential role of data quality, availability, and extractability in implementing effective AI applications in oncology. By employing a multifaceted methodology, including literature review, data readiness assessment, and expert workshops, the study addresses the challenges of integrating AI into clinical decision-making. The research identifies crucial data points for skin cancer treatment decisions, evaluates their presence and quality in various information systems, and highlights the difficulties in extracting information from unstructured data. The findings underline the significance of high-quality, accessible data for the success of AI-driven CDSS in medical settings, particularly in the complex field of oncology.

AI-Driven Decision Support in Oncology: Evaluating Data Readiness for Skin Cancer Treatment

TL;DR

The paper addresses the readiness of clinical data to support AI-driven decision support in oncology, focusing on skin cancer treatment. It introduces a data-centric AI-readiness framework and applies a six-step methodology at the Skin Tumor Center of the University Hospital Münster to assess data sources, extractability, and quality. The study identifies 41 decision-relevant data points, with substantial portions residing in unstructured text and cancer registries, revealing substantial barriers to real-world AI CDSS deployment. It emphasizes the need for standardized, comprehensive data documentation—including social and patient-centered factors—and outlines future work to expand datasets and determine sample sizes for an analogy-based CDSS. Overall, the work highlights data quality and availability as pivotal for effective AI-enhanced oncologic decision-making and provides a practical roadmap for data preparation in this domain.

Abstract

This research focuses on evaluating and enhancing data readiness for the development of an Artificial Intelligence (AI)-based Clinical Decision Support System (CDSS) in the context of skin cancer treatment. The study, conducted at the Skin Tumor Center of the University Hospital Münster, delves into the essential role of data quality, availability, and extractability in implementing effective AI applications in oncology. By employing a multifaceted methodology, including literature review, data readiness assessment, and expert workshops, the study addresses the challenges of integrating AI into clinical decision-making. The research identifies crucial data points for skin cancer treatment decisions, evaluates their presence and quality in various information systems, and highlights the difficulties in extracting information from unstructured data. The findings underline the significance of high-quality, accessible data for the success of AI-driven CDSS in medical settings, particularly in the complex field of oncology.

Paper Structure

This paper contains 15 sections, 1 figure, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data Quality and Clinical Decision Support
  4. AI Readiness
  5. Materials and Methods
  6. Preparation
  7. Data Source Identification
  8. Sample Data Extraction
  9. Data Discovery
  10. Questionnaire
  11. Workshops with Domain Experts
  12. Evaluation
  13. Results
  14. Summary and conclusions
  15. Questionnaire

Figures (1)

  • Figure 1: The methodological approach was divided into the following steps: Preparation (1.) describes essential tasks that form the basis for the further procedure. Data Source Identification (2a.) describes the procedure for determining the correct data sources. Sampla Data Extraction (2b.) describes the export and transfer of medical data. Data Discovery (2c.) describes the evaluation of data suitability within the context of an AI project. Questionnaire (3a.) describes the development of the questionnaire, which enables the collection of decision-relevant data and their prioritization. Workshops with Domain Experts (3c.) describes the organization of the workshops in which the results of the questionnaire were discussed. Evaluation (4.) describes the examination of the data relevant for a treatment decision.