scholarly journals Support systems to guide clinical decision-making in precision oncology: The Cancer Core Europe Molecular Tumor Board Portal

2020 ◽  
Vol 26 (7) ◽  
pp. 992-994 ◽  
Author(s):  
David Tamborero ◽  
◽  
Rodrigo Dienstmann ◽  
Maan Haj Rachid ◽  
Jorrit Boekel ◽  
...  
2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 11035-11035
Author(s):  
Kristen Marrone ◽  
Jessica Tao ◽  
Jenna VanLiere Canzoniero ◽  
Paola Ghanem ◽  
Emily Nizialek ◽  
...  

11035 Background: The accelerated impact of next generation sequencing (NGS) in clinical decision making requires the integration of cancer genomics and precision oncology focused training into medical oncology education. The Johns Hopkins Molecular Tumor Board (JH MTB) is a multi-disciplinary effort focused on integration of NGS findings with critical evidence interpretation to generate personalized recommendations tailored to the genetic footprint of individual patients. Methods: The JH MTB and the Medical Oncology Fellowship Program have developed a 3-month precision oncology elective for fellows in their research years. Commencing fall of 2020, the goals of this elective are to enhance the understanding of NGS platforms and findings, advance the interpretation and characterization of molecular assay outputs by use of mutation annotators and knowledgebases and ultimately master the art of matching NGS findings with available therapies. Fellow integration into the MTB focuses on mentored case-based learning in mutation characterization and ranking by levels of evidence for actionability, with culmination in form of verbal presentations and written summary reports of final MTB recommendations. A mixed methods questionnaire was administered to evaluate progress since elective initiation. Results: Three learners who have participated as of February 2021 were included. Of the two who had completed the MTB elective, each have presented at least 10 cases, with at least 1 scholarly publication planned. All indicated strong agreement that MTB elective had increased their comfort with interpreting clinical NGS reports as well as the use of knowledgebases and variant annotators. Exposure to experts in the field of molecular precision oncology, identification of resources necessary to interpret clinical NGS reports, development of ability to critically assess various NGS platforms, and gained familiarity with computational analyses relevant to clinical decision making were noted as strengths of the MTB elective. Areas of improvement included ongoing initiatives that involve streamlining variant annotation and transcription of information for written reports. Conclusions: A longitudinal elective in the JHU MTB has been found to be preliminarily effective in promoting knowledge mastery and creating academic opportunities related to the clinical application of precision medicine. Future directions will include leveraging of the MTB infrastructure for research projects, learner integration into computational laboratory meetings, and expansion of the MTB curriculum to include different levels of learners from multiple medical education programs. Continued elective participation will be key to understanding how best to facilitate adaptive expertise in assigning clinical relevance to genomic findings, ultimately improving precision medicine delivery in patient care and trial development.


2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 3128-3128
Author(s):  
Meena Sadaps ◽  
Kathryn Demski ◽  
Ying Ni ◽  
Vicky Konig ◽  
Brandie Leach ◽  
...  

3128 Background: Multidisciplinary molecular tumor boards were first established with the onset of precision oncology (PO), as many clinicians were unfamiliar with the interpretation and incorporation of the information into clinical practice. PO has since rapidly evolved and integrated itself into standard of care practices for most cancer patients, yet molecular tumor boards have not grown accordingly and in fact some have been discontinued. There remains a paucity of data in regards to the value and impact of molecular tumor board discussions themselves. We previously reported on our longitudinal experiences in PO ( Sadaps et al, 2018), focusing on the therapeutic impact of matched therapy. Here, we report on the utility of our molecular tumor board in clinical decision making. Methods: We conducted a retrospective review of patients seen at Cleveland Clinic with a solid tumor malignancy who had large panel, next-generation-sequencing (NGS) performed via any commercial platform from November 2019-January 2021. Cases were filtered through a local therapeutic algorithm and then reviewed individually. Initial review was performed by a core genomics committee comprised of 2 oncologists and 2 genetic counselors. Interesting and/or complex cases were flagged for discussion at our bimonthly molecular tumor board, which is regularly attended by medical oncologists, pathologists, genetic counselors, bioinformaticians, and patient care coordinators. Data analyzed included categorization of treatment recommendations and the percentage of cases for which initial recommendations were changed based on tumor board discussion. Results: Of 782 total cases, 575 (73.5%) had a clinically relevant genomics tumor board (GTB) recommendation as compared to 51.7% from our previously reported study. 16.7% of patients had on label recommendation(s) and 86.4% had off label/ clinical trial recommendation(s). 179 (22.9%) patients were recommended for genetic counseling (GC). During our bimonthly GTB, we discussed 173 (22.1%) of these cases. Of the discussed cases, the most common tumor types were hepatobiliary (18.5%), lower gastrointestinal (17.3%), and breast (16.2%). Topics of discussion at GTB included such things as pathologic/histologic/molecular testing, prioritization of available trials, appropriateness of an off label therapy, and need for a genetics consult. Discussion at GTB resulted in a change in treatment recommendation in 63 (36.4%) cases. Conclusions: Discussions from multidisciplinary molecular tumor board impacted treatment decisions for our patients. Referral to GC was also common and should be considered an integral part of somatic sequencing review. Molecular tumor boards remain a crucial platform for treatment guidance and clinical management, especially given the increase in “actionability” over the years due to newly discovered targets and targeted therapies in this rapidly evolving field.


Author(s):  
Jan Kalina

The complexity of clinical decision-making is immensely increasing with the advent of big data with a clinical relevance. Clinical decision systems represent useful e-health tools applicable to various tasks within the clinical decision-making process. This chapter is devoted to basic principles of clinical decision support systems and their benefits for healthcare and patient safety. Big data is crucial input for clinical decision support systems and is helpful in the task to find the diagnosis, prognosis, and therapy. Statistical challenges of analyzing big data in psychiatry are overviewed, with a particular interest for psychiatry. Various barriers preventing telemedicine tools from expanding to the field of mental health are discussed. The development of decision support systems is claimed here to play a key role in the development of information-based medicine, particularly in psychiatry. Information technology will be ultimately able to combine various information sources including big data to present and enforce a holistic information-based approach to psychiatric care.


2020 ◽  
pp. 167-186
Author(s):  
Steven Walczak

Clinical decision support systems are meant to improve the quality of decision-making in healthcare. Artificial intelligence is the science of creating intelligent systems that solve complex problems at the level of or better than human experts. Combining artificial intelligence methods into clinical decision support will enable the utilization of large quantities of data to produce relevant decision-making information to practitioners. This article examines various artificial intelligence methodologies and shows how they may be incorporated into clinical decision-making systems. A framework for describing artificial intelligence applications in clinical decision support systems is presented.


2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 1568-1568
Author(s):  
Navdeep Dehar ◽  
Tasnima Abedin ◽  
Patricia A. Tang ◽  
D. Gwyn Bebb ◽  
Winson Y. Cheung

1568 Background: With the increasing number and frequency of biomarker and genetic tests that are offered to patients with cancer, it is important to ensure that they fully understand the implications of these tests. In this survey study, we aimed to compare the attitudes and expectations of patients and cancer physicians about the role of biomarker and genetic testing in clinical decision-making. Methods: Two separate, complimentary, self-administered questionnaires for cancer patients and their physicians, respectively, were collected in Calgary, Alberta, Canada. Survey responses from patients were subsequently matched with those of their corresponding oncologists to form patient–oncologist dyads. We determined the concordance rates between responses of patients and those of their oncologists. Results: A total of 113 patients and 15 physicians participated in the study from July to September 2019. Patients demonstrated good understanding of general cancer biology (79%) and diagnostic processes (91%) associated with precision oncology. About 70% patients were willing to undergo minor procedures, and participate in research involving biomarker or genetic testing; however, this was over-estimated by their physicians in 82% of cases. Many patients felt that their tumor should be tested to guide treatment (70%) and were not bothered by potential delays in treatment due to testing (23%). These views from patients were largely shared by their oncologists (concordance 64%). While only 28% patients thought that they had enough knowledge to make informed decisions, majority (68%) said that they needed more information. Importantly, knowledge and expectations regarding the applications of biomarker or genetic test results on actual diagnosis and prognosis were grossly discrepant between patients and their oncologists (concordance 26% and 36%, respectively). Conclusions: Patients and cancer physicians tend to be aware of the advances in precision oncology and are willing to participate in biomarker and genetic testing and research. However, they do not consistently agree about the roles and applications of these tests, which may result in misplaced expectations. Strategies to improve education and communication are needed to align these expectations and improve the quality of clinical decision-making.


2020 ◽  
pp. 390-409
Author(s):  
Steven Walczak

Clinical decision support systems are meant to improve the quality of decision-making in healthcare. Artificial intelligence is the science of creating intelligent systems that solve complex problems at the level of or better than human experts. Combining artificial intelligence methods into clinical decision support will enable the utilization of large quantities of data to produce relevant decision-making information to practitioners. This article examines various artificial intelligence methodologies and shows how they may be incorporated into clinical decision-making systems. A framework for describing artificial intelligence applications in clinical decision support systems is presented.


Author(s):  
Jan Kalina

The complexity of clinical decision-making is immensely increasing with the advent of big data with a clinical relevance. Clinical decision systems represent useful e-health tools applicable to various tasks within the clinical decision-making process. This chapter is devoted to basic principles of clinical decision support systems and their benefits for healthcare and patient safety. Big data is crucial input for clinical decision support systems and is helpful in the task to find the diagnosis, prognosis, and therapy. Statistical challenges of analyzing big data in psychiatry are overviewed, with a particular interest for psychiatry. Various barriers preventing telemedicine tools from expanding to the field of mental health are discussed. The development of decision support systems is claimed here to play a key role in the development of information-based medicine, particularly in psychiatry. Information technology will be ultimately able to combine various information sources including big data to present and enforce a holistic information-based approach to psychiatric care.


2018 ◽  
Vol 3 (2) ◽  
pp. 31-47 ◽  
Author(s):  
Steven Walczak

Clinical decision support systems are meant to improve the quality of decision-making in healthcare. Artificial intelligence is the science of creating intelligent systems that solve complex problems at the level of or better than human experts. Combining artificial intelligence methods into clinical decision support will enable the utilization of large quantities of data to produce relevant decision-making information to practitioners. This article examines various artificial intelligence methodologies and shows how they may be incorporated into clinical decision-making systems. A framework for describing artificial intelligence applications in clinical decision support systems is presented.


Sign in / Sign up

Export Citation Format

Share Document