Toward cognitive pipelines of medical assistance algorithms
- 308 Downloads
Assistance algorithms for medical tasks have great potential to support physicians with their daily work. However, medicine is also one of the most demanding domains for computer-based support systems, since medical assistance tasks are complex and the practical experience of the physician is crucial. Recent developments in the area of cognitive computing appear to be well suited to tackle medicine as an application domain.
We propose a system based on the idea of cognitive computing and consisting of auto-configurable medical assistance algorithms and their self-adapting combination. The system enables automatic execution of new algorithms, given they are made available as Medical Cognitive Apps and are registered in a central semantic repository. Learning components can be added to the system to optimize the results in the cases when numerous Medical Cognitive Apps are available for the same task. Our prototypical implementation is applied to the areas of surgical phase recognition based on sensor data and image progressing for tumor progression mappings.
Our results suggest that such assistance algorithms can be automatically configured in execution pipelines, candidate results can be automatically scored and combined, and the system can learn from experience. Furthermore, our evaluation shows that the Medical Cognitive Apps are providing the correct results as they did for local execution and run in a reasonable amount of time.
The proposed solution is applicable to a variety of medical use cases and effectively supports the automated and self-adaptive configuration of cognitive pipelines based on medical interpretation algorithms.
KeywordsComputer aided medicine Semantic Web Phase recognition Tumor progression mapping Cognitive architecture
This work was carried out with the support of the German Research Foundation (DFG) within projects I01, A01, R01, S01 and I04, SFB/TRR 125 “Cognition-Guided Surgery”.
Compliance with ethical standards
Conflict of interest
Patrick Philipp, Maria Maleshkova, Darko Katic, Christian Weber, Michael Götz, Stefanie Speidel, Achim Rettinger, Benedikt Kämpgen, Marco Nolden, Anna-Laura Wekerle, Rüdiger Dillmann, Hannes Kenngott, Beat Müller and Rudi Studer declare that they have no conflict of interest.
- 1.Ferrucci D (2010) Build watson: an overview of deepqa for the jeopardy challenge. In: Proceedings of international conference on parallel architecture and compilation techniques, ACM pp 1–2Google Scholar
- 4.Oinn T, Greenwood M, Addis M, Alpdemir MN, Ferris J, Glover K, Goble C, Goderis A, Hull D, Marvin D, Li P, Lord P, Pocock MR, Senger M, Stevens R, Wipat A, Wroe C (2006) Taverna: lessons in creating a workflow environment for the life sciences. Concurr Comput Pract Exp 18(10):1067–1100CrossRefGoogle Scholar
- 5.Wood I, Vandervalk B, McCarthy L, Wilkinson M (2012) OWL-DL domain-models as abstract workflows. In: Margaria T, Steffen B (eds) Leveraging applications of formal methods, verification and validation. Applications and case studies. Volume 7610 of lecture notes in computer science. Springer, Berlin, pp 56–66CrossRefGoogle Scholar
- 6.Beygelzimer A, Riabov A, Sow D, Turaga DS, Udrea O (2013) Big data exploration via automated orchestration of analytic workflows. In: Proceedings of international conference on autonomic computing, San Jose, CA, pp 153–158Google Scholar
- 7.Brazdil P, Carrier CG, Soares C, Vilalta R (2008) Metalearning: applications to data mining. Springer, BerlinGoogle Scholar
- 8.Nguyen P, Hilario M, Kalousis A (2014) Using meta-mining to support data mining workflow planning and optimization. J Artif Intell Res 51:605–644Google Scholar
- 9.Kotthoff L (2014) Algorithm selection for combinatorial search problems: a survey. AI Mag 35(3):48–60Google Scholar
- 10.Thornton C, Hutter F, Hoos HH, Leyton-Brown K (2013) Auto-weka: combined selection and hyperparameter optimization of classification algorithms. In: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM pp 847–855Google Scholar
- 11.Samulowitz H, Sabharwal A, Reddy C (2014) Cognitive automation of data science. In: ICML AutoML workshopGoogle Scholar
- 15.Neumuth T, Strau G, Meixensberger J, Lemke H, Burgert O (2006) Acquisition of process descriptions from surgical interventions. Database and expert systems applications. Volume 4080 of lecture notes in computer science. Springer, Berlin, pp 602–611Google Scholar
- 17.Speidel S, Benzko J, Krappe S, Sudra G, Azad P, Müller-Stich BP, Gutt C, Dillmann R (2009) Automatic classification of minimally invasive instruments based on endoscopic image sequences, vol 7261. In: Proceedings of SPIEGoogle Scholar
- 18.Neumuth T, Jannin P, Strauss G, Meixensberger J, Burgert O (2009) Validation of knowledge acquisition for surgical process models. J Am Med Inf Assoc 16(1):72–80Google Scholar
- 19.Katic D, Wekerle AL, Gärtner F, Kenngott HG, Müller-Stich BP, Dillmann R, Speidel S (2014) Knowledge-driven formalization of laparoscopic surgeries for rule-based intraoperative context-aware assistance. In: IPCAIGoogle Scholar
- 20.Gemmeke P, Maleshkova M, Philipp P, Götz M, Weber C, Kämpgen B, Zelzer S, Maier-Hein K, Rettinger A (2014) Using linked data and Web APIs for automating the pre-processing of medical images. COLD (ISWC)Google Scholar
- 21.Philipp P, Maleshkova M, Götz M, Weber C, Kämpgen B, Zelzer S, Maier-Hein K, Rettinger A (2015) Automatisierte Verarbeitung von Bildverarbeitungsalgorithmen mit semantischen Technologien. In: BVMGoogle Scholar
- 22.Krötzsch M, Vrandečić D, Völkel M (2006) Semantic mediawiki. In: The Semantic Web-ISWC 2006. Springer, pp 935–942Google Scholar
- 23.Speiser S, Harth A (2011) Integrating linked data and services with linked data services. In: The semantic web: research and appl. Springer 170–184Google Scholar
- 25.Freund Y, Schapire RE (1995) A desicion-theoretic generalization of on-line learning and an application to boosting. In: Vitányi P (ed) Computational learning theory. Springer, Heidelberg, pp 23–37Google Scholar
- 26.Breiman L (1996) Bagging predictors. Mach learn 24(2):123–140Google Scholar
- 29.Stadtmüller S, Speiser S, Harth A, Studer R (2013) Data-fu: a language and an interpreter for interaction with read/write linked data. In: Proceedings of the international conference on World Wide Web, pp 1225–1236Google Scholar