mario cypko - Academia.edu (original) (raw)
Papers by mario cypko
Mensch und Computer 2022
Current robotic systems in surgery are telemanipulators, but the future will likely be more autom... more Current robotic systems in surgery are telemanipulators, but the future will likely be more automated. Past and current developments literally put the robotic system at the center of the action, and force the surgical team to adapt to it. In addition to important advantages of robotic surgery, empirical studies identify serious disadvantages in sensory perception and team communication, leading to decreased situational awareness among the surgeon and the team. We therefore raise two interrelated questions: Which actors of a surgical team should be part of a controlled, semi-automated robotic assistance and how should the collaborative interaction between the actors (including the robot) be designed. Previous research has examined the situation awareness in robotic-assisted surgeries with bedside assistant, being either residents or specifically trained registered nurse first assistants, with advantages of one over the other. We built on this work by observing for the first time robotic-assisted surgeries with highly experienced bedside assistants, senior surgeons. We found that a senior surgeon in this role excelled once again, for example, through lively medical discussions and independent problem solving, and was more likely to give us clues about a thoughtful development of semi-autonomous, collaborative surgical robots. These new insights will form the basis for subsequent interviews in which surgical teams will reflect on their expectations of the robotic agency. Our overarching goal is then to translate the results into new user interface designs for robotic surgery through repeated cycles of participatory design workshops and expert evaluations.
Treatment decision-making in head and neck oncology is gaining complexity by the increasing evide... more Treatment decision-making in head and neck oncology is gaining complexity by the increasing evidence pointing towards more individualized and selective treatment options. Therefore, decision making in multidisciplinary teams is becoming the key point in the clinical pathways. Clinical decision-support systems based on Bayesian networks can support complex decision-making processes by providing mathematically correct and transparent advises. In the last three decades, different clinical applications of Bayesian networks have been proposed. Because appropriate data for model learning and testing is often unobtainable, expert modeling is required. To decrease the modeling and validation effort, networks usually represent small or highly simplified decision structures. However, especially systems for supporting multidisciplinary treatment decisions may only gain a user’s confidence if the systems’ results are comprehensive and comprehensible. Challenges in developing such systems relate...
Einleitung: Das zunehmende Verständnis der Komplexität von onkologischen Erkrankungen und die ste... more Einleitung: Das zunehmende Verständnis der Komplexität von onkologischen Erkrankungen und die steigende Menge an verfügbaren Patienteninformationen ermöglichen in vielen Fällen eine personalisierte Behandlung, erschweren aber oft auch die Wahl der bestmöglichen Behandlung[for full text, please go to the a.m. URL]
Clinical decision-making for complex diseases such as cancer aims at finding the right diagnosis,... more Clinical decision-making for complex diseases such as cancer aims at finding the right diagnosis, optimal treatment or best aftercare for a specific patient. The decision-making process is very challenging due to the distributed storage of patient information entities in multiple hospital information systems, the required inclusion of multiple clinical disciplines with their different views of disease and therapy, and the multitude of available medical examinations, therapy options and aftercare strategies. Clinical Decision Support Systems (CDSS) address these difficulties by presenting all relevant information entities in a concise manner and providing a recommendation based on interdisciplinary disease- and patient-specific models of diagnosis and treatment. This work summarizes our research on visual assistance for therapy decision-making. We aim at supporting the preparation and implementation of expert meetings discussing cancer cases (tumor boards) and the aftercare consultat...
GMS Current Posters in Otorhinolaryngology - Head and Neck Surgery, Apr 26, 2017
Einleitung: In die Therapieentscheidung onkologischer Krankheitsbilder wie Kopf-Hals-Tumore fließ... more Einleitung: In die Therapieentscheidung onkologischer Krankheitsbilder wie Kopf-Hals-Tumore fließen viele Charakteristiken, die im interdisziplinären Kopf-Hals-Tumorboard (HN-TB) von Experten verschiedener Fachdisziplinen diskutiert werden, um eine optimale Therapie zu finden. Dabei spielen fachspezifische Sichtweisen (FS) eine Rolle. Ziel ist die Analyse und Integration dieser FS in das digitale Patientenmodell (DPM) "Larynxkarzinom" (LC), das auf Basis eines Bayes'schen Netzwerks konstruiert wurde. Methoden: Die Analyse der FS erfolgte durch Literaturrecherche und Befragung von Experten aus verschiedenen Fachdisziplinen (u.a. HNO, Strahlenmedizin, klinische Onkologie). Diese Informationen wurden in das DPM LC integriert und sollen in geeigneten Visualisierungskonzepten für die klinische Anwendung zur Verfügung stehen. Im Rahmen einer kleinen Studie wurde die Intuition und Handhabbarkeit der Visualisierung untersucht. Aktuell besteht das DPM LC aus über 1300 Informati...
Einleitung: Die Therapieentscheidung bei Patienten mit Kopf-Hals-Tumoren (HNC) wird auf Basis vie... more Einleitung: Die Therapieentscheidung bei Patienten mit Kopf-Hals-Tumoren (HNC) wird auf Basis vieler Informationsentitäten (IEs) im interdisziplinären Kopf-Hals-Tumorboard (HN-TB) getroffen. Grundlegend ist das TNM-Klassifikationssystem (TNM), das durch verschiedene diagnostische Verfahren[for full text, please go to the a.m. URL]
Abstract- und Posterband – 90. Jahresversammlung der Deutschen Gesellschaft für HNO-Heilkunde, Kopf- und Hals-Chirurgie e.V., Bonn – Digitalisierung in der HNO-Heilkunde, 2019
Einleitung: Komplexe Krankheitsbilder wie Kopf-Hals-Tumore (HNC) werden im interdisziplinären Kop... more Einleitung: Komplexe Krankheitsbilder wie Kopf-Hals-Tumore (HNC) werden im interdisziplinären Kopf-Hals-Tumorboard (HN-TB) evaluiert, um aus den vielen Informationsentitäten (IEs) eines Patienten die beste Therapie abzuleiten. Das digitale Patientenmodell (DPM) "Larynxkarzinom"[zum vollständigen Text gelangen Sie über die oben angegebene URL]
Einleitung: Besonders bei komplexen Krankheitsbildern wie Kopf-Hals-Tumoren (HNC) sind Therapieen... more Einleitung: Besonders bei komplexen Krankheitsbildern wie Kopf-Hals-Tumoren (HNC) sind Therapieentscheidungen von vielen variablen Faktoren (Klassifikatoren, Tumorbiologie etc.) abhängig. Moderne informatische Modellierungsverfahren können helfen, alle für die Therapieentscheidung relevanten[for full text, please go to the a.m. URL]
Der Chirurg, 2020
Vor weniger als zehn Jahren ist es in der Welt der Informatik und künstlichen Intelligenz (KI) mi... more Vor weniger als zehn Jahren ist es in der Welt der Informatik und künstlichen Intelligenz (KI) mit der Verwendung tiefer neuronaler Netze zu einem Durchbruch gekommen, der zunächst in der Medizin kaum Beachtung fand. Im Jahre 2017 erschienen dann erste hochrangige Publikationen zu medizinischen Anwendung von KI. Das Potenzial wurde nun vielen bewusst, und zwar sowohl in der klinischen Medizin als auch in der klinischen und biomedizinischen Forschung. Ende 2019 sehen wir uns in einer Umbruchphase: Erste Konzepte zur regulatorischen Handhabe sind erschienen, eine Vielzahl an Start-ups, aber auch etablierte Konzerne versuchen sich daran, auf KI basierende Medizinprodukte in den Markt einzuführen. In dem Beitrag werden die Grundlagen zum Verständnis KI-basierter Medizinprodukte erörtert sowie ein Einblick in gegenwärtige auf KI-basierte Lösungen speziell in der Herzchirurgie gegeben. Less than 10 years ago a breakthrough was made in the world of computer science and artificial intelligence (AI) with the application of deep neural networks, which initially found little attention in medicine. In 2017 the first high-ranking publications on the medical application of AI were published. The potential of AI became known to many both in clinical medicine as well as in clinical and biomedical research. At the end of 2019 a phase of upheaval is occurring: first concepts for regulatory procedures have appeared, a large number of start-ups but also established companies are endeavoring to introduce AI-based medical devices into the market. This article discusses the basic principles for understanding AI-based medical devices as well as an overview of current AI-based solutions specific to cardiac surgery.
Increasing knowledge leads to more complex decision making. In previous work, we developed a syst... more Increasing knowledge leads to more complex decision making. In previous work, we developed a system that supports clinical experts in the decision-making process. The system is built upon probabilistic networks, which are particularly suited for modeling complex decisions, and can comprise all relevant[zum vollständigen Text gelangen Sie über die oben angegebene URL]
Studies in Health Technology and Informatics, 2017
During the diagnostic process a lot of information is generated. All this information is assessed... more During the diagnostic process a lot of information is generated. All this information is assessed when making a final diagnosis and planning the therapy. While some patient information is stable, e.g., gender, others may become outdated, e.g., tumor size derived from CT data. Quantifying this information up-to-dateness and deriving consequences are difficult. Especially for the implementation in clinical decision support systems, this has not been studied. When information entities tend to become outdated, in practice, clinicians intuitively reduce their impact when making decisions. Therefore, in a system's calculations their impact should be reduced as well. We propose a method of decreasing the certainty of information entities based on their up-to-dateness. The method is tested in a decision support system for TNM staging based on Bayesian networks. We compared the actual N-state in records of 39 patients to the N-state calculated with and without decreasing data certainty. ...
Studies in Health Technology and Informatics, 2016
Clinical decision support systems (CDSS) are developed to facilitate physicians' decision mak... more Clinical decision support systems (CDSS) are developed to facilitate physicians' decision making, particularly for complex, oncological diseases. Access to relevant patient specific information from electronic health records (EHR) is limited to the structure and transmission formats in the respective hospital information system. We propose a system-architecture for a standardized access to patient specific information for a CDSS for laryngeal cancer. Following the idea of a CDSS using Bayesian Networks, we developed an architecture concept applying clinical standards. We recommend the application of Arden Syntax for the definition and processing of needed medical knowledge and clinical information, as well as the use of HL7 FHIR to identify the relevant data elements in an EHR to increase the interoperability the CDSS.
Development of Clinical Decision Support Systems using Bayesian Networks
Development of Clinical Decision Support Systems using Bayesian Networks
Patient-specific Bayesian Network in a Clinical Environment "If used properly, clinical decision ... more Patient-specific Bayesian Network in a Clinical Environment "If used properly, clinical decision support systems have the potential to change the way medicine has been taught and practiced."-Berner, 2007.
Development of Clinical Decision Support Systems using Bayesian Networks
Development of a Clinical Decision Support System Introduction CDSSs aim for improving clinical d... more Development of a Clinical Decision Support System Introduction CDSSs aim for improving clinical decision-making and patient safety [88]. They can improve patient care by "providing the right information to the right person at the right point in workflow in the right intervention format through the right channel" [126]. CDSSs may support decisions passively, e.g., by error recognitions using computerized physician order entry (CPOE) and monitoring a patient situation, or actively, e.g., by providing alerts in unusual or dangerous situations, recommending medications, and supporting physicians to find optimal decisions. Active decision support systems that require a rethinking and reorganizing of decisions and health care plans from clinicians (e.g., support for diagnostic and treatment decisions) are more likely to fail their acceptance [154]. In such cases, clinicians ignore or overwrite the decisions of a system and, finally, stop using it. Once a CDSS is built, its clinical acceptance depends on an appropriate integration, by means of both its technical adaption to existing clinical systems, specifically to the local electronic health record (EHR), as well as user-friendly interfaces. Well developed and clinically integrated, CDSSs can minimize errors, promote patient safety, save time and, finally, decrease the costs of care [88]. A successful CDSS development and clinical integration requires to reach one of these expected benefits without impairing the remaining, or at least to increase the cost-benefit ratio [88] The work of Berner et al. [12] reviews CDSSs to investigate their impact and effectiveness on clinical decision-making and points out various challenges. Challenges concern technical issues, such as data integration, system development, issues around the vocabulary, system output and maintenance, as well as organizational and personal issues, such as vendors, developers and users, and, finally, legal and ethical issues. To address all these
Mensch und Computer 2022
Current robotic systems in surgery are telemanipulators, but the future will likely be more autom... more Current robotic systems in surgery are telemanipulators, but the future will likely be more automated. Past and current developments literally put the robotic system at the center of the action, and force the surgical team to adapt to it. In addition to important advantages of robotic surgery, empirical studies identify serious disadvantages in sensory perception and team communication, leading to decreased situational awareness among the surgeon and the team. We therefore raise two interrelated questions: Which actors of a surgical team should be part of a controlled, semi-automated robotic assistance and how should the collaborative interaction between the actors (including the robot) be designed. Previous research has examined the situation awareness in robotic-assisted surgeries with bedside assistant, being either residents or specifically trained registered nurse first assistants, with advantages of one over the other. We built on this work by observing for the first time robotic-assisted surgeries with highly experienced bedside assistants, senior surgeons. We found that a senior surgeon in this role excelled once again, for example, through lively medical discussions and independent problem solving, and was more likely to give us clues about a thoughtful development of semi-autonomous, collaborative surgical robots. These new insights will form the basis for subsequent interviews in which surgical teams will reflect on their expectations of the robotic agency. Our overarching goal is then to translate the results into new user interface designs for robotic surgery through repeated cycles of participatory design workshops and expert evaluations.
Treatment decision-making in head and neck oncology is gaining complexity by the increasing evide... more Treatment decision-making in head and neck oncology is gaining complexity by the increasing evidence pointing towards more individualized and selective treatment options. Therefore, decision making in multidisciplinary teams is becoming the key point in the clinical pathways. Clinical decision-support systems based on Bayesian networks can support complex decision-making processes by providing mathematically correct and transparent advises. In the last three decades, different clinical applications of Bayesian networks have been proposed. Because appropriate data for model learning and testing is often unobtainable, expert modeling is required. To decrease the modeling and validation effort, networks usually represent small or highly simplified decision structures. However, especially systems for supporting multidisciplinary treatment decisions may only gain a user’s confidence if the systems’ results are comprehensive and comprehensible. Challenges in developing such systems relate...
Einleitung: Das zunehmende Verständnis der Komplexität von onkologischen Erkrankungen und die ste... more Einleitung: Das zunehmende Verständnis der Komplexität von onkologischen Erkrankungen und die steigende Menge an verfügbaren Patienteninformationen ermöglichen in vielen Fällen eine personalisierte Behandlung, erschweren aber oft auch die Wahl der bestmöglichen Behandlung[for full text, please go to the a.m. URL]
Clinical decision-making for complex diseases such as cancer aims at finding the right diagnosis,... more Clinical decision-making for complex diseases such as cancer aims at finding the right diagnosis, optimal treatment or best aftercare for a specific patient. The decision-making process is very challenging due to the distributed storage of patient information entities in multiple hospital information systems, the required inclusion of multiple clinical disciplines with their different views of disease and therapy, and the multitude of available medical examinations, therapy options and aftercare strategies. Clinical Decision Support Systems (CDSS) address these difficulties by presenting all relevant information entities in a concise manner and providing a recommendation based on interdisciplinary disease- and patient-specific models of diagnosis and treatment. This work summarizes our research on visual assistance for therapy decision-making. We aim at supporting the preparation and implementation of expert meetings discussing cancer cases (tumor boards) and the aftercare consultat...
GMS Current Posters in Otorhinolaryngology - Head and Neck Surgery, Apr 26, 2017
Einleitung: In die Therapieentscheidung onkologischer Krankheitsbilder wie Kopf-Hals-Tumore fließ... more Einleitung: In die Therapieentscheidung onkologischer Krankheitsbilder wie Kopf-Hals-Tumore fließen viele Charakteristiken, die im interdisziplinären Kopf-Hals-Tumorboard (HN-TB) von Experten verschiedener Fachdisziplinen diskutiert werden, um eine optimale Therapie zu finden. Dabei spielen fachspezifische Sichtweisen (FS) eine Rolle. Ziel ist die Analyse und Integration dieser FS in das digitale Patientenmodell (DPM) "Larynxkarzinom" (LC), das auf Basis eines Bayes'schen Netzwerks konstruiert wurde. Methoden: Die Analyse der FS erfolgte durch Literaturrecherche und Befragung von Experten aus verschiedenen Fachdisziplinen (u.a. HNO, Strahlenmedizin, klinische Onkologie). Diese Informationen wurden in das DPM LC integriert und sollen in geeigneten Visualisierungskonzepten für die klinische Anwendung zur Verfügung stehen. Im Rahmen einer kleinen Studie wurde die Intuition und Handhabbarkeit der Visualisierung untersucht. Aktuell besteht das DPM LC aus über 1300 Informati...
Einleitung: Die Therapieentscheidung bei Patienten mit Kopf-Hals-Tumoren (HNC) wird auf Basis vie... more Einleitung: Die Therapieentscheidung bei Patienten mit Kopf-Hals-Tumoren (HNC) wird auf Basis vieler Informationsentitäten (IEs) im interdisziplinären Kopf-Hals-Tumorboard (HN-TB) getroffen. Grundlegend ist das TNM-Klassifikationssystem (TNM), das durch verschiedene diagnostische Verfahren[for full text, please go to the a.m. URL]
Abstract- und Posterband – 90. Jahresversammlung der Deutschen Gesellschaft für HNO-Heilkunde, Kopf- und Hals-Chirurgie e.V., Bonn – Digitalisierung in der HNO-Heilkunde, 2019
Einleitung: Komplexe Krankheitsbilder wie Kopf-Hals-Tumore (HNC) werden im interdisziplinären Kop... more Einleitung: Komplexe Krankheitsbilder wie Kopf-Hals-Tumore (HNC) werden im interdisziplinären Kopf-Hals-Tumorboard (HN-TB) evaluiert, um aus den vielen Informationsentitäten (IEs) eines Patienten die beste Therapie abzuleiten. Das digitale Patientenmodell (DPM) "Larynxkarzinom"[zum vollständigen Text gelangen Sie über die oben angegebene URL]
Einleitung: Besonders bei komplexen Krankheitsbildern wie Kopf-Hals-Tumoren (HNC) sind Therapieen... more Einleitung: Besonders bei komplexen Krankheitsbildern wie Kopf-Hals-Tumoren (HNC) sind Therapieentscheidungen von vielen variablen Faktoren (Klassifikatoren, Tumorbiologie etc.) abhängig. Moderne informatische Modellierungsverfahren können helfen, alle für die Therapieentscheidung relevanten[for full text, please go to the a.m. URL]
Der Chirurg, 2020
Vor weniger als zehn Jahren ist es in der Welt der Informatik und künstlichen Intelligenz (KI) mi... more Vor weniger als zehn Jahren ist es in der Welt der Informatik und künstlichen Intelligenz (KI) mit der Verwendung tiefer neuronaler Netze zu einem Durchbruch gekommen, der zunächst in der Medizin kaum Beachtung fand. Im Jahre 2017 erschienen dann erste hochrangige Publikationen zu medizinischen Anwendung von KI. Das Potenzial wurde nun vielen bewusst, und zwar sowohl in der klinischen Medizin als auch in der klinischen und biomedizinischen Forschung. Ende 2019 sehen wir uns in einer Umbruchphase: Erste Konzepte zur regulatorischen Handhabe sind erschienen, eine Vielzahl an Start-ups, aber auch etablierte Konzerne versuchen sich daran, auf KI basierende Medizinprodukte in den Markt einzuführen. In dem Beitrag werden die Grundlagen zum Verständnis KI-basierter Medizinprodukte erörtert sowie ein Einblick in gegenwärtige auf KI-basierte Lösungen speziell in der Herzchirurgie gegeben. Less than 10 years ago a breakthrough was made in the world of computer science and artificial intelligence (AI) with the application of deep neural networks, which initially found little attention in medicine. In 2017 the first high-ranking publications on the medical application of AI were published. The potential of AI became known to many both in clinical medicine as well as in clinical and biomedical research. At the end of 2019 a phase of upheaval is occurring: first concepts for regulatory procedures have appeared, a large number of start-ups but also established companies are endeavoring to introduce AI-based medical devices into the market. This article discusses the basic principles for understanding AI-based medical devices as well as an overview of current AI-based solutions specific to cardiac surgery.
Increasing knowledge leads to more complex decision making. In previous work, we developed a syst... more Increasing knowledge leads to more complex decision making. In previous work, we developed a system that supports clinical experts in the decision-making process. The system is built upon probabilistic networks, which are particularly suited for modeling complex decisions, and can comprise all relevant[zum vollständigen Text gelangen Sie über die oben angegebene URL]
Studies in Health Technology and Informatics, 2017
During the diagnostic process a lot of information is generated. All this information is assessed... more During the diagnostic process a lot of information is generated. All this information is assessed when making a final diagnosis and planning the therapy. While some patient information is stable, e.g., gender, others may become outdated, e.g., tumor size derived from CT data. Quantifying this information up-to-dateness and deriving consequences are difficult. Especially for the implementation in clinical decision support systems, this has not been studied. When information entities tend to become outdated, in practice, clinicians intuitively reduce their impact when making decisions. Therefore, in a system's calculations their impact should be reduced as well. We propose a method of decreasing the certainty of information entities based on their up-to-dateness. The method is tested in a decision support system for TNM staging based on Bayesian networks. We compared the actual N-state in records of 39 patients to the N-state calculated with and without decreasing data certainty. ...
Studies in Health Technology and Informatics, 2016
Clinical decision support systems (CDSS) are developed to facilitate physicians' decision mak... more Clinical decision support systems (CDSS) are developed to facilitate physicians' decision making, particularly for complex, oncological diseases. Access to relevant patient specific information from electronic health records (EHR) is limited to the structure and transmission formats in the respective hospital information system. We propose a system-architecture for a standardized access to patient specific information for a CDSS for laryngeal cancer. Following the idea of a CDSS using Bayesian Networks, we developed an architecture concept applying clinical standards. We recommend the application of Arden Syntax for the definition and processing of needed medical knowledge and clinical information, as well as the use of HL7 FHIR to identify the relevant data elements in an EHR to increase the interoperability the CDSS.
Development of Clinical Decision Support Systems using Bayesian Networks
Development of Clinical Decision Support Systems using Bayesian Networks
Patient-specific Bayesian Network in a Clinical Environment "If used properly, clinical decision ... more Patient-specific Bayesian Network in a Clinical Environment "If used properly, clinical decision support systems have the potential to change the way medicine has been taught and practiced."-Berner, 2007.
Development of Clinical Decision Support Systems using Bayesian Networks
Development of a Clinical Decision Support System Introduction CDSSs aim for improving clinical d... more Development of a Clinical Decision Support System Introduction CDSSs aim for improving clinical decision-making and patient safety [88]. They can improve patient care by "providing the right information to the right person at the right point in workflow in the right intervention format through the right channel" [126]. CDSSs may support decisions passively, e.g., by error recognitions using computerized physician order entry (CPOE) and monitoring a patient situation, or actively, e.g., by providing alerts in unusual or dangerous situations, recommending medications, and supporting physicians to find optimal decisions. Active decision support systems that require a rethinking and reorganizing of decisions and health care plans from clinicians (e.g., support for diagnostic and treatment decisions) are more likely to fail their acceptance [154]. In such cases, clinicians ignore or overwrite the decisions of a system and, finally, stop using it. Once a CDSS is built, its clinical acceptance depends on an appropriate integration, by means of both its technical adaption to existing clinical systems, specifically to the local electronic health record (EHR), as well as user-friendly interfaces. Well developed and clinically integrated, CDSSs can minimize errors, promote patient safety, save time and, finally, decrease the costs of care [88]. A successful CDSS development and clinical integration requires to reach one of these expected benefits without impairing the remaining, or at least to increase the cost-benefit ratio [88] The work of Berner et al. [12] reviews CDSSs to investigate their impact and effectiveness on clinical decision-making and points out various challenges. Challenges concern technical issues, such as data integration, system development, issues around the vocabulary, system output and maintenance, as well as organizational and personal issues, such as vendors, developers and users, and, finally, legal and ethical issues. To address all these