1
|
Sloss EA, McPherson JP, Beck AC, Guo JW, Scheese CH, Flake NR, Chalkidis G, Staes CJ. Patient and Caregiver Perceptions of an Interface Design to Communicate Artificial Intelligence-Based Prognosis for Patients With Advanced Solid Tumors. JCO Clin Cancer Inform 2024; 8:e2300187. [PMID: 38657194 DOI: 10.1200/cci.23.00187] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 02/22/2024] [Accepted: 03/07/2024] [Indexed: 04/26/2024] Open
Abstract
PURPOSE Use of artificial intelligence (AI) in cancer care is increasing. What remains unclear is how best to design patient-facing systems that communicate AI output. With oncologist input, we designed an interface that presents patient-specific, machine learning-based 6-month survival prognosis information designed to aid oncology providers in preparing for and discussing prognosis with patients with advanced solid tumors and their caregivers. The primary purpose of this study was to assess patient and caregiver perceptions and identify enhancements of the interface for communicating 6-month survival and other prognosis information when making treatment decisions concerning anticancer and supportive therapy. METHODS This qualitative study included interviews and focus groups conducted between November and December 2022. Purposive sampling was used to recruit former patients with cancer and/or former caregivers of patients with cancer who had participated in cancer treatment decisions from Utah or elsewhere in the United States. Categories and themes related to perceptions of the interface were identified. RESULTS We received feedback from 20 participants during eight individual interviews and two focus groups, including four cancer survivors, 13 caregivers, and three representing both. Overall, most participants expressed positive perceptions about the tool and identified its value for supporting decision making, feeling less alone, and supporting communication among oncologists, patients, and their caregivers. Participants identified areas for improvement and implementation considerations, particularly that oncologists should share the tool and guide discussions about prognosis with patients who want to receive the information. CONCLUSION This study revealed important patient and caregiver perceptions of and enhancements for the proposed interface. Originally designed with input from oncology providers, patient and caregiver participants identified additional interface design recommendations and implementation considerations to support communication about prognosis.
Collapse
Affiliation(s)
| | - Jordan P McPherson
- Huntsman Cancer Institute, University of Utah, Salt Lake City, UT
- College of Pharmacy, University of Utah, Salt Lake City, UT
| | - Anna C Beck
- Huntsman Cancer Institute, University of Utah, Salt Lake City, UT
| | - Jia-Wen Guo
- College of Nursing, University of Utah, Salt Lake City, UT
- Department of Biomedical Informatics, University of Utah, Salt Lake City, UT
| | - Carolyn H Scheese
- College of Nursing, University of Utah, Salt Lake City, UT
- Department of Biomedical Informatics, University of Utah, Salt Lake City, UT
| | - Naomi R Flake
- Clinical & Translational Science Institute, University of Utah, Salt Lake City, UT
| | | | - Catherine J Staes
- College of Nursing, University of Utah, Salt Lake City, UT
- Department of Biomedical Informatics, University of Utah, Salt Lake City, UT
| |
Collapse
|
2
|
Staes CJ, Beck AC, Chalkidis G, Scheese CH, Taft T, Guo JW, Newman MG, Kawamoto K, Sloss EA, McPherson JP. Design of an interface to communicate artificial intelligence-based prognosis for patients with advanced solid tumors: a user-centered approach. J Am Med Inform Assoc 2023; 31:174-187. [PMID: 37847666 PMCID: PMC10746322 DOI: 10.1093/jamia/ocad201] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2023] [Revised: 09/18/2023] [Accepted: 10/02/2023] [Indexed: 10/19/2023] Open
Abstract
OBJECTIVES To design an interface to support communication of machine learning (ML)-based prognosis for patients with advanced solid tumors, incorporating oncologists' needs and feedback throughout design. MATERIALS AND METHODS Using an interdisciplinary user-centered design approach, we performed 5 rounds of iterative design to refine an interface, involving expert review based on usability heuristics, input from a color-blind adult, and 13 individual semi-structured interviews with oncologists. Individual interviews included patient vignettes and a series of interfaces populated with representative patient data and predicted survival for each treatment decision point when a new line of therapy (LoT) was being considered. Ongoing feedback informed design decisions, and directed qualitative content analysis of interview transcripts was used to evaluate usability and identify enhancement requirements. RESULTS Design processes resulted in an interface with 7 sections, each addressing user-focused questions, supporting oncologists to "tell a story" as they discuss prognosis during a clinical encounter. The iteratively enhanced interface both triggered and reflected design decisions relevant when attempting to communicate ML-based prognosis, and exposed misassumptions. Clinicians requested enhancements that emphasized interpretability over explainability. Qualitative findings confirmed that previously identified issues were resolved and clarified necessary enhancements (eg, use months not days) and concerns about usability and trust (eg, address LoT received elsewhere). Appropriate use should be in the context of a conversation with an oncologist. CONCLUSION User-centered design, ongoing clinical input, and a visualization to communicate ML-related outcomes are important elements for designing any decision support tool enabled by artificial intelligence, particularly when communicating prognosis risk.
Collapse
Affiliation(s)
- Catherine J Staes
- College of Nursing, University of Utah, Salt Lake City, UT 84112, United States
- Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, UT 84108, United States
| | - Anna C Beck
- Department of Internal Medicine, Huntsman Cancer Institute, University of Utah, Salt Lake City, UT 84112, United States
| | - George Chalkidis
- Healthcare IT Research Department, Center for Digital Services, Hitachi Ltd., Tokyo, Japan
| | - Carolyn H Scheese
- College of Nursing, University of Utah, Salt Lake City, UT 84112, United States
- Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, UT 84108, United States
| | - Teresa Taft
- Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, UT 84108, United States
| | - Jia-Wen Guo
- College of Nursing, University of Utah, Salt Lake City, UT 84112, United States
- Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, UT 84108, United States
| | - Michael G Newman
- Department of Population Sciences, Huntsman Cancer Institute, Salt Lake City, UT 84112, United States
| | - Kensaku Kawamoto
- Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, UT 84108, United States
| | - Elizabeth A Sloss
- College of Nursing, University of Utah, Salt Lake City, UT 84112, United States
| | - Jordan P McPherson
- Department of Pharmacotherapy, College of Pharmacy, University of Utah, Salt Lake City, UT 84108, United States
- Department of Pharmacy, Huntsman Cancer Institute, Salt Lake City, UT 84112, United States
| |
Collapse
|
3
|
Chalkidis G, McPherson JP, Beck A, Newman MG, Guo JW, Sloss EA, Staes CJ. External Validation of a Machine Learning Model to Predict 6-Month Mortality for Patients With Advanced Solid Tumors. JAMA Netw Open 2023; 6:e2327193. [PMID: 37535359 PMCID: PMC10401299 DOI: 10.1001/jamanetworkopen.2023.27193] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 08/04/2023] Open
Affiliation(s)
| | - Jordan P McPherson
- Huntsman Cancer Institute, Salt Lake City, Utah
- College of Pharmacy, University of Utah, Salt Lake City
| | - Anna Beck
- Huntsman Cancer Institute, Salt Lake City, Utah
| | | | - Jia-Wen Guo
- College of Nursing, University of Utah, Salt Lake City
- Department of Biomedical Informatics, University of Utah, Salt Lake City
| | | | - Catherine J Staes
- College of Nursing, University of Utah, Salt Lake City
- Department of Biomedical Informatics, University of Utah, Salt Lake City
| |
Collapse
|
4
|
Chalkidis G, McPherson J, Beck A, Newman M, Yui S, Staes C. Development of a Machine Learning Model Using Limited Features to Predict 6-Month Mortality at Treatment Decision Points for Patients With Advanced Solid Tumors. JCO Clin Cancer Inform 2022; 6:e2100163. [PMID: 35467965 PMCID: PMC9067363 DOI: 10.1200/cci.21.00163] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
Patients with advanced solid tumors may receive intensive treatments near the end of life. This study aimed to create a machine learning (ML) model using limited features to predict 6-month mortality at treatment decision points (TDPs). Predicting 6-month mortality at treatment decisions for patients with advanced solid tumors.![]()
Collapse
Affiliation(s)
| | | | - Anna Beck
- Huntsman Cancer Institute, Salt Lake City, UT
| | | | | | | |
Collapse
|
5
|
Tarumi S, Takeuchi W, Chalkidis G, Rodriguez-Loya S, Kuwata J, Flynn M, Turner KM, Sakaguchi FH, Weir C, Kramer H, Shields DE, Warner PB, Kukhareva P, Ban H, Kawamoto K. Leveraging Artificial Intelligence to Improve Chronic Disease Care: Methods and Application to Pharmacotherapy Decision Support for Type-2 Diabetes Mellitus. Methods Inf Med 2021; 60:e32-e43. [PMID: 33975376 PMCID: PMC8294941 DOI: 10.1055/s-0041-1728757] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
OBJECTIVES Artificial intelligence (AI), including predictive analytics, has great potential to improve the care of common chronic conditions with high morbidity and mortality. However, there are still many challenges to achieving this vision. The goal of this project was to develop and apply methods for enhancing chronic disease care using AI. METHODS Using a dataset of 27,904 patients with diabetes, an analytical method was developed and validated for generating a treatment pathway graph which consists of models that predict the likelihood of alternate treatment strategies achieving care goals. An AI-driven clinical decision support system (CDSS) integrated with the electronic health record (EHR) was developed by encapsulating the prediction models in an OpenCDS Web service module and delivering the model outputs through a SMART on FHIR (Substitutable Medical Applications and Reusable Technologies on Fast Healthcare Interoperability Resources) web-based dashboard. This CDSS enables clinicians and patients to review relevant patient parameters, select treatment goals, and review alternate treatment strategies based on prediction results. RESULTS The proposed analytical method outperformed previous machine-learning algorithms on prediction accuracy. The CDSS was successfully integrated with the Epic EHR at the University of Utah. CONCLUSION A predictive analytics-based CDSS was developed and successfully integrated with the EHR through standards-based interoperability frameworks. The approach used could potentially be applied to many other chronic conditions to bring AI-driven CDSS to the point of care.
Collapse
Affiliation(s)
- Shinji Tarumi
- Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
| | - Wataru Takeuchi
- Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
| | - George Chalkidis
- Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
| | - Salvador Rodriguez-Loya
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
| | - Junichi Kuwata
- Department of Product Design, Center for Social Innovation, Hitachi Ltd., Kokubunji, Tokyo, Japan
| | - Michael Flynn
- Departments of Internal Medicine and Pediatrics, University of Utah, Salt Lake City, Utah, United States
| | - Kyle M Turner
- Department of Pharmacotherapy, University of Utah, Salt Lake City, Utah, United States
| | - Farrant H Sakaguchi
- Department of Family and Preventive Medicine, University of Utah, Salt Lake City, Utah, United States
| | - Charlene Weir
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
| | - Heidi Kramer
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
| | - David E Shields
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
| | - Phillip B Warner
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
| | - Polina Kukhareva
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
| | - Hideyuki Ban
- Department of Media Intelligent Processing Research, Center for Technology Innovation Artificial Intelligence, Hitachi Ltd., Kokubunji, Tokyo, Japan
| | - Kensaku Kawamoto
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, United States
| |
Collapse
|
6
|
Anazawa T, Uchiho Y, Yokoi T, Chalkidis G, Yamazaki M. A simple and highly sensitive spectroscopic fluorescence-detection system for multi-channel plastic-microchip electrophoresis based on side-entry laser-beam zigzag irradiation. Lab Chip 2017; 17:2235-2242. [PMID: 28585967 DOI: 10.1039/c7lc00448f] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
A five-color fluorescence-detection system for eight-channel plastic-microchip electrophoresis was developed. In the eight channels (with effective electrophoretic lengths of 10 cm), single-stranded DNA fragments were separated (with single-base resolution up to 300 bases within 10 min), and seventeen-loci STR genotyping for forensic human identification was successfully demonstrated. In the system, a side-entry laser beam is passed through the eight channels (eight A channels), with alternately arrayed seven sacrificial channels (seven B channels), by a technique called "side-entry laser-beam zigzag irradiation." Laser-induced fluorescence from the eight A channels and Raman-scattered light from the seven B channels are then simultaneously, uniformly, and spectroscopically detected, in the direction perpendicular to the channel array plane, through a transmission grating and a CCD camera. The system is therefore simple and highly sensitive. Because the microchip is fabricated by plastic-injection molding, it is inexpensive and disposable and thus suitable for actual use in various fields.
Collapse
Affiliation(s)
| | | | | | | | - Motohiro Yamazaki
- Hitachi High-Technologies Corporation, Science & Medical Systems Business Group, Japan
| |
Collapse
|
7
|
Yoshida K, Sanada M, Shiraishi Y, Nowak D, Nagata Y, Yamamoto R, Sato Y, Sato-Otsubo A, Kon A, Nagasaki M, Chalkidis G, Suzuki Y, Shiosaka M, Kawahata R, Yamaguchi T, Otsu M, Obara N, Sakata-Yanagimoto M, Ishiyama K, Mori H, Nolte F, Hofmann WK, Miyawaki S, Sugano S, Haferlach C, Koeffler H, Shih LY, Haferlach T, Chiba S, Nakauchi H, Miyano S, Ogawa S. Abstract 5119: Frequent splicing pathway mutations and aberrant RNA splicing in myelodysplasia. Cancer Res 2012. [DOI: 10.1158/1538-7445.am2012-5119] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Abstract
MDS are a group of myeloid neoplasms characterized by deregulated blood cell production and a high propensity to AML. Although a number of gene alterations have been implicated in the pathogenesis of MDS, they do not fully explain the pathogenesis of MDS. So, in order to clarify a comprehensive registry of gene mutations in MDS, we performed whole-exome sequencing of 29 cases with MDS and related myeloid neoplasm. A total of 268 somatic mutations or 9.2 mutations per sample were identified. Among these 9 genes were mutated in more than 2 cases, which not only included a spectrum of known gene targets in MDS, but also affected previously unknown genes that are commonly involved in RNA splicing pathway, including U2AF35, SRSF2 and ZRSR2. Together with additional three (SF3A1, SF3B1 and PRPF40B) found in single cases, 16 (55.2%) of the 29 discovery cases carried a mutation affecting the component of the splicing machinery. To confirm the observation, we examined 9 spliceosome genes for mutations in a large set of myeloid neoplasms. In total, 219 mutations were identified in 209 out of the 582 samples of myeloid neoplasms. RNA splicing pathway mutations were highly specific to myelodysplasia, including 19 of 23 (83%) cases with RARS, 43 of 50 (86%) RCMD-RS, 68 of 155 (44%) other MDS, 48 of 88 (55%) CMML, and 16 of 62 (26%) secondary AML with MDS features with a string preference of SF3B1 mutations to RARS and RCMD-RS and of SRSF2 to CMML, while they were rare in cases with de novo AML and MPN. Significantly, these mutations occurred in an almost completely mutually exclusive manner among mutated cases, suggesting the importance of deregulated RNA splicing in the pathogenesis of MDS. RNA splicing plays critical roles in differentiation, development, and disease and is a major source for protein diversity in higher eukaryotes. Splicing pathway mutations in myelodysplasia commonly affected those components of the splicing complex that are engaged in the 3′ splice site recognition, strongly indicating production of unspliced or aberrantly spliced RNA species are incriminated for the pathogenesis of MDS. So, to clarify the effect of these splicing mutations on RNA splicing, we expressed the wild-type and the mutant U2AF35 or SRSF2 in HeLa cells and performed whole transcriptome analysis in these cells. The results of exon array showed that the wild-type U2AF35 promoted RNA splicing correctly, whereas the mutant U2AF35 inhibited this processes and rendered intronic sequences to remain unspliced. RNA sequencing additionally showed that the number of reads that encompassed the exon/intron junctions was significantly increased in mutant U2AF35-transduced cells. This result means that mutant U2AF35 actually induced impaired 3′-splice site recognition during pre-mRNA processing. In conclusion, our study demonstrated that abnormal RNA splicing caused by mutations of multiple genes on RNA splicing pathway is a common feature of myelodysplasia.
Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 103rd Annual Meeting of the American Association for Cancer Research; 2012 Mar 31-Apr 4; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2012;72(8 Suppl):Abstract nr 5119. doi:1538-7445.AM2012-5119
Collapse
Affiliation(s)
| | | | | | - Daniel Nowak
- 3University Hospital Mannheim, Mannheim, Germany
| | | | - Ryo Yamamoto
- 2Institute of Medical Science, Univ. of Tokyo, Tokyo, Japan
| | - Yusuke Sato
- 1Cancer Genomics Project, Univ. of Tokyo, Tokyo, Japan
| | | | - Ayana Kon
- 1Cancer Genomics Project, Univ. of Tokyo, Tokyo, Japan
| | - Masao Nagasaki
- 2Institute of Medical Science, Univ. of Tokyo, Tokyo, Japan
| | | | - Yutaka Suzuki
- 2Institute of Medical Science, Univ. of Tokyo, Tokyo, Japan
| | | | | | | | - Makoto Otsu
- 2Institute of Medical Science, Univ. of Tokyo, Tokyo, Japan
| | | | | | - Ken Ishiyama
- 5Tokyo Metropolitan Ohtsuka Hospital, Tokyo, Japan
| | - Hiraku Mori
- 6Showa University Fujigaoka Hospital, Tokyo, Japan
| | | | | | | | - Sumio Sugano
- 2Institute of Medical Science, Univ. of Tokyo, Tokyo, Japan
| | | | | | | | | | | | | | - Satoru Miyano
- 2Institute of Medical Science, Univ. of Tokyo, Tokyo, Japan
| | - Seishi Ogawa
- 1Cancer Genomics Project, Univ. of Tokyo, Tokyo, Japan
| |
Collapse
|