Cognitive Algorithms and digitized Tissue – based Diagnosis
Aims: To analyze the nature and impact of cognitive algorithms and programming on digitized tissue – based diagnosis. Definitions: Digitized tissue – based diagnosis includes all computerized tissue investigations that contribute to the most appropriate description and forecast of the actual pati...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
DiagnomX
2017-07-01
|
| Series: | Diagnostic Pathology |
| Online Access: | http://www.diagnosticpathology.eu/content/index.php/dpath/article/view/248 |
| _version_ | 1811311708103245824 |
|---|---|
| author | Jürgen Görtler Klaus Kayser Stephan Borkenfeld Rita Carvalho Gian Kayser |
| author_facet | Jürgen Görtler Klaus Kayser Stephan Borkenfeld Rita Carvalho Gian Kayser |
| author_sort | Jürgen Görtler |
| collection | DOAJ |
| description | Aims: To analyze the nature and impact of cognitive algorithms and programming on digitized tissue – based diagnosis.
Definitions: Digitized tissue – based diagnosis includes all computerized tissue investigations that contribute to the most appropriate description and forecast of the actual patient’s disease [1]. Cognitive algorithms are programs that encompass machine learning, reasoning, and human – computer interaction [2].
Theoretical considerations: Digitized blood data, objective clinical findings, microscopic, gross, radiological images and gene alterations are analyzed by specialized image analysis methods, and transferred in numbers and vectors. These are analyzed by statistical procedures. They include higher order statistics such as multivariate analysis, neural networks and ‘black box’ strategies, for example ‘deep learning’ or ‘Watson’ approaches. These algorithms can be applied at different cognitive ‘levels’, to reach a digital decision for different procedures which should assist the patient’s health condition. These levels can be grouped in self learning, self promoting, self targeting, and self exploring algorithms. Each of them requires a memory and neighbourhood condition. Self targeting and exploring algorithms are circumscribed mechanisms with singularities and repair procedures. They develop self recognition.
Consecutives: Medical doctors including pathologists are commonly not trained to understand the basic principles and workflow of applied or potential future procedures. At present, basic medical data only serve for simple cognitive algorithms. Most of the investigations focus on ‘deep learning’ procedures. The applied learning and decision algorithms might be modified and themselves be used for ‘next order cognitive algorithms’. Such systems will develop their own strategies, and become independent from potential human interactions. The basic strategy of such IT systems is described herein.
Perspectives: Medical doctors including pathologists should be aware about the abilities to enhance their work by supporting tools. In some case the users may not be able to fully understand these tools. Furthermore, these tools will probably become self learning, and, therefore, seem to propose the daily workflow probably without any medical control or even interaction. |
| first_indexed | 2024-04-13T10:23:39Z |
| format | Article |
| id | doaj.art-18c81df30c0540beac4ac7d0a76e24cb |
| institution | Directory Open Access Journal |
| issn | 2364-4893 |
| language | English |
| last_indexed | 2024-04-13T10:23:39Z |
| publishDate | 2017-07-01 |
| publisher | DiagnomX |
| record_format | Article |
| series | Diagnostic Pathology |
| spelling | doaj.art-18c81df30c0540beac4ac7d0a76e24cb2022-12-22T02:50:24ZengDiagnomXDiagnostic Pathology2364-48932017-07-013110.17629/www.diagnosticpathology.eu-2017-3:248Cognitive Algorithms and digitized Tissue – based DiagnosisJürgen Görtler0Klaus Kayser1Stephan Borkenfeld2Rita Carvalho3Gian Kayser4IBM Global Markets, Systems, Frankfurt, GermanyCharite, Berlin, GermanyIAT, Heidelberg, GermanyCentral Lisbon Hospital Center, Department of Pathology, Lisbon, PortugalInstitute of Surgical Pathology, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg, GermanyAims: To analyze the nature and impact of cognitive algorithms and programming on digitized tissue – based diagnosis. Definitions: Digitized tissue – based diagnosis includes all computerized tissue investigations that contribute to the most appropriate description and forecast of the actual patient’s disease [1]. Cognitive algorithms are programs that encompass machine learning, reasoning, and human – computer interaction [2]. Theoretical considerations: Digitized blood data, objective clinical findings, microscopic, gross, radiological images and gene alterations are analyzed by specialized image analysis methods, and transferred in numbers and vectors. These are analyzed by statistical procedures. They include higher order statistics such as multivariate analysis, neural networks and ‘black box’ strategies, for example ‘deep learning’ or ‘Watson’ approaches. These algorithms can be applied at different cognitive ‘levels’, to reach a digital decision for different procedures which should assist the patient’s health condition. These levels can be grouped in self learning, self promoting, self targeting, and self exploring algorithms. Each of them requires a memory and neighbourhood condition. Self targeting and exploring algorithms are circumscribed mechanisms with singularities and repair procedures. They develop self recognition. Consecutives: Medical doctors including pathologists are commonly not trained to understand the basic principles and workflow of applied or potential future procedures. At present, basic medical data only serve for simple cognitive algorithms. Most of the investigations focus on ‘deep learning’ procedures. The applied learning and decision algorithms might be modified and themselves be used for ‘next order cognitive algorithms’. Such systems will develop their own strategies, and become independent from potential human interactions. The basic strategy of such IT systems is described herein. Perspectives: Medical doctors including pathologists should be aware about the abilities to enhance their work by supporting tools. In some case the users may not be able to fully understand these tools. Furthermore, these tools will probably become self learning, and, therefore, seem to propose the daily workflow probably without any medical control or even interaction.http://www.diagnosticpathology.eu/content/index.php/dpath/article/view/248 |
| spellingShingle | Jürgen Görtler Klaus Kayser Stephan Borkenfeld Rita Carvalho Gian Kayser Cognitive Algorithms and digitized Tissue – based Diagnosis Diagnostic Pathology |
| title | Cognitive Algorithms and digitized Tissue – based Diagnosis |
| title_full | Cognitive Algorithms and digitized Tissue – based Diagnosis |
| title_fullStr | Cognitive Algorithms and digitized Tissue – based Diagnosis |
| title_full_unstemmed | Cognitive Algorithms and digitized Tissue – based Diagnosis |
| title_short | Cognitive Algorithms and digitized Tissue – based Diagnosis |
| title_sort | cognitive algorithms and digitized tissue based diagnosis |
| url | http://www.diagnosticpathology.eu/content/index.php/dpath/article/view/248 |
| work_keys_str_mv | AT jurgengortler cognitivealgorithmsanddigitizedtissuebaseddiagnosis AT klauskayser cognitivealgorithmsanddigitizedtissuebaseddiagnosis AT stephanborkenfeld cognitivealgorithmsanddigitizedtissuebaseddiagnosis AT ritacarvalho cognitivealgorithmsanddigitizedtissuebaseddiagnosis AT giankayser cognitivealgorithmsanddigitizedtissuebaseddiagnosis |