1
|
Lennerz JK, Salgado R, Kim GE, Sirintrapun SJ, Thierauf JC, Singh A, Indave I, Bard A, Weissinger SE, Heher YK, de Baca ME, Cree IA, Bennett S, Carobene A, Ozben T, Ritterhouse LL. Diagnostic quality model (DQM): an integrated framework for the assessment of diagnostic quality when using AI/ML. Clin Chem Lab Med 2023; 61:544-557. [PMID: 36696602 DOI: 10.1515/cclm-2022-1151] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2022] [Accepted: 01/13/2023] [Indexed: 01/26/2023]
Abstract
BACKGROUND Laboratory medicine has reached the era where promises of artificial intelligence and machine learning (AI/ML) seem palpable. Currently, the primary responsibility for risk-benefit assessment in clinical practice resides with the medical director. Unfortunately, there is no tool or concept that enables diagnostic quality assessment for the various potential AI/ML applications. Specifically, we noted that an operational definition of laboratory diagnostic quality - for the specific purpose of assessing AI/ML improvements - is currently missing. METHODS A session at the 3rd Strategic Conference of the European Federation of Laboratory Medicine in 2022 on "AI in the Laboratory of the Future" prompted an expert roundtable discussion. Here we present a conceptual diagnostic quality framework for the specific purpose of assessing AI/ML implementations. RESULTS The presented framework is termed diagnostic quality model (DQM) and distinguishes AI/ML improvements at the test, procedure, laboratory, or healthcare ecosystem level. The operational definition illustrates the nested relationship among these levels. The model can help to define relevant objectives for implementation and how levels come together to form coherent diagnostics. The affected levels are referred to as scope and we provide a rubric to quantify AI/ML improvements while complying with existing, mandated regulatory standards. We present 4 relevant clinical scenarios including multi-modal diagnostics and compare the model to existing quality management systems. CONCLUSIONS A diagnostic quality model is essential to navigate the complexities of clinical AI/ML implementations. The presented diagnostic quality framework can help to specify and communicate the key implications of AI/ML solutions in laboratory diagnostics.
Collapse
Affiliation(s)
- Jochen K Lennerz
- Department of Pathology, Massachusetts General Hospital/Harvard Medical, Boston, MA, USA
| | - Roberto Salgado
- Department of Pathology, GZA-ZNA Hospitals, Antwerp, Belgium
- Division of Research, Peter Mac Callum Cancer Centre, Melbourne, Australia
| | - Grace E Kim
- Department of Pathology, University of California San Francisco, San Francisco, CA, USA
| | | | - Julia C Thierauf
- Department of Pathology, Massachusetts General Hospital/Harvard Medical, Boston, MA, USA
- Department of Otorhinolaryngology, Head and Neck Surgery, German Cancer Research Center (DKFZ), Heidelberg University Hospital and Research Group Molecular Mechanisms of Head and Neck Tumors, Heidelberg, Germany
| | - Ankit Singh
- Department of Pathology, Massachusetts General Hospital/Harvard Medical, Boston, MA, USA
| | - Iciar Indave
- European Monitoring Centre for Drugs and Drug Addiction (EMCDDA), Lisbon, Portugal
| | - Adam Bard
- Department of Pathology, Massachusetts General Hospital/Harvard Medical, Boston, MA, USA
| | | | - Yael K Heher
- Department of Pathology, Massachusetts General Hospital/Harvard Medical, Boston, MA, USA
| | | | - Ian A Cree
- International Agency for Research on Cancer (IARC), World Health Organization, Lyon, France
| | - Shannon Bennett
- Department of Laboratory Medicine and Pathology (DLMP), Mayo Clinic, Rochester, MN, USA
| | - Anna Carobene
- IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Tomris Ozben
- Medical Faculty, Dept. of Clinical Biochemistry, Akdeniz University, Antalya, Türkiye
- Medical Faculty, Clinical and Experimental Medicine, Ph.D. Program, University of Modena and Reggio Emilia, Modena, Italy
| | - Lauren L Ritterhouse
- Department of Pathology, Massachusetts General Hospital/Harvard Medical, Boston, MA, USA
| |
Collapse
|
2
|
Artificial Intelligence and Cardiovascular Genetics. Life (Basel) 2022; 12:life12020279. [PMID: 35207566 PMCID: PMC8875522 DOI: 10.3390/life12020279] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2021] [Revised: 01/26/2022] [Accepted: 02/09/2022] [Indexed: 12/13/2022] Open
Abstract
Polygenic diseases, which are genetic disorders caused by the combined action of multiple genes, pose unique and significant challenges for the diagnosis and management of affected patients. A major goal of cardiovascular medicine has been to understand how genetic variation leads to the clinical heterogeneity seen in polygenic cardiovascular diseases (CVDs). Recent advances and emerging technologies in artificial intelligence (AI), coupled with the ever-increasing availability of next generation sequencing (NGS) technologies, now provide researchers with unprecedented possibilities for dynamic and complex biological genomic analyses. Combining these technologies may lead to a deeper understanding of heterogeneous polygenic CVDs, better prognostic guidance, and, ultimately, greater personalized medicine. Advances will likely be achieved through increasingly frequent and robust genomic characterization of patients, as well the integration of genomic data with other clinical data, such as cardiac imaging, coronary angiography, and clinical biomarkers. This review discusses the current opportunities and limitations of genomics; provides a brief overview of AI; and identifies the current applications, limitations, and future directions of AI in genomics.
Collapse
|
3
|
Bruehl FK, Kim AS, Li MM, Lindeman NI, Moncur JT, Souers RJ, Vasalos P, Voelkerding KV, Xian RR, Surrey LF. Tiered Somatic Variant Classification Adoption Has Increased Worldwide With Some Practice Differences Based on Location and Institutional Setting. Arch Pathol Lab Med 2022; 146:822-832. [PMID: 34979564 DOI: 10.5858/arpa.2021-0179-cp] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/27/2021] [Indexed: 11/06/2022]
Abstract
CONTEXT.— The 2017 Association for Molecular Pathology/American Society of Clinical Oncology/College of American Pathologists (CAP) tier classification guideline provides a framework to standardize interpretation and reporting of somatic variants. OBJECTIVE.— To evaluate the adoption and performance of the 2017 guideline among laboratories performing somatic next-generation sequencing (NGS). DESIGN.— A survey was distributed to laboratories participating in NGS CAP proficiency testing for solid tumors (NGSST) and hematologic malignancies (NGSHM). RESULTS.— Worldwide, 64.4% (152 of 236) of NGSST and 66.4% (87 of 131) of NGSHM participants used tier classification systems, of which the 2017 guideline was used by 84.9% (129 of 152) of NGSST and 73.6% (64 of 87) of NGSHM participants. The 2017 guideline was modified by 24.4% (30 of 123) of NGSST and 21.7% (13 of 60) of NGSHM laboratories. Laboratories implementing the 2017 guideline were satisfied or very satisfied (74.2% [89 of 120] NGSST and 69.5% [41 of 59] NGSHM), and the impression of tier classification reproducibility was high (mean of 3.9 [NGSST] and 3.6 [NGSHM] on a 5-point scale). Of nonusers, 35.2% (38 of 108) of NGSST and 39.4% (26 of 66) of NGSHM laboratories were planning implementation. For future guideline revisions, respondents favored including variants to monitor disease (63.9% [78 of 122] NGSST, 80.0% [48 of 60] NGSHM) and germline variants (55.3% [63 of 114] NGSST, 75.0% [45 of 60] NGSHM). Additional subtiers were not favored by academic laboratories compared to nonacademic laboratories (P < .001 NGSST and P = .02 NGSHM). CONCLUSIONS.— The 2017 guideline has been implemented by more than 50.0% of CAP laboratories. While most laboratories using the 2017 guideline report satisfaction, thoughtful guideline modifications may further enhance the quality, reproducibility, and clinical utility of the 2017 guideline for tiered somatic variant classification.
Collapse
Affiliation(s)
- Frido K Bruehl
- From Robert J. Tomsich Pathology and Laboratory Medicine Institute, Cleveland Clinic, Cleveland, Ohio (Bruehl)
| | - Annette S Kim
- The Departments of Pathology, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts (Kim, Lindeman)
| | - Marilyn M Li
- The Department of Pathology and Laboratory Medicine, Perelman School of Medicine, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania (Li, Surrey)
| | - Neal I Lindeman
- The Departments of Pathology, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts (Kim, Lindeman)
| | - Joel T Moncur
- The Joint Pathology Center, Office of the Director, Silver Spring, Maryland (Moncur), College of American Pathologists, Northfield, Illinois
| | - Rhona J Souers
- Biostatistics Department (Souers), College of American Pathologists, Northfield, Illinois
| | - Patricia Vasalos
- Proficiency Testing (Vasalos), College of American Pathologists, Northfield, Illinois
| | | | - Rena R Xian
- The Department of Pathology and Oncology, School of Medicine, Johns Hopkins University, Baltimore, Maryland (Xian)
| | - Lea F Surrey
- The Department of Pathology and Laboratory Medicine, Perelman School of Medicine, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania (Li, Surrey)
| |
Collapse
|
4
|
Haymond S, McCudden C. Rise of the Machines: Artificial Intelligence and the Clinical Laboratory. J Appl Lab Med 2021; 6:1640-1654. [PMID: 34379752 DOI: 10.1093/jalm/jfab075] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2021] [Accepted: 06/08/2021] [Indexed: 11/14/2022]
Abstract
BACKGROUND Artificial intelligence (AI) is rapidly being developed and implemented to augment and automate decision-making across healthcare systems. Being an essential part of these systems, laboratories will see significant growth in AI applications for the foreseeable future. CONTENT In laboratory medicine, AI can be used for operational decision-making and automating or augmenting human-based workflows. Specific applications include instrument automation, error detection, forecasting, result interpretation, test utilization, genomics, and image analysis. If not doing so today, clinical laboratories will be using AI routinely in the future, therefore, laboratory experts should understand their potential role in this new area and the opportunities for AI technologies. The roles of laboratorians range from passive provision of data to fuel algorithms to developing entirely new algorithms, with subject matter expertise as a perfect fit in the middle. The technical development of algorithms is only a part of the overall picture, where the type, availability, and quality of data are at least as important. Implementation of AI algorithms also offers technical and usability challenges that need to be understood to be successful. Finally, as AI algorithms continue to become available, it is important to understand how to evaluate their validity and utility in the real world. SUMMARY This review provides an overview of what AI is, examples of how it is currently being used in laboratory medicine, different ways for laboratorians to get involved in algorithm development, and key considerations for AI algorithm implementation and critical evaluation.
Collapse
Affiliation(s)
- Shannon Haymond
- Department of Pathology, Northwestern University Feinberg School of Medicine, Chicago, IL.,Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, IL
| | - Christopher McCudden
- Department of Pathology & Laboratory Medicine, University of Ottawa, Canada, The Ottawa Hospital, and the Eastern Ontario Regional Laboratory Association, Canada
| |
Collapse
|
5
|
Jäger N. Bioinformatics workflows for clinical applications in precision oncology. Semin Cancer Biol 2021; 84:103-112. [PMID: 33476720 DOI: 10.1016/j.semcancer.2020.12.020] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2020] [Revised: 12/15/2020] [Accepted: 12/28/2020] [Indexed: 12/23/2022]
Abstract
High-throughput molecular profiling of tumors is a fundamental aspect of precision oncology, enabling the identification of genomic alterations that can be targeted therapeutically. In this context, a patient is matched to a specific drug or therapy based on the tumor's underlying genetic driver events rather than the histologic classification. This approach requires extensive bioinformatics methodology and workflows, including raw sequencing data processing and quality control, variant calling and annotation, integration of different molecular data types, visualization and finally reporting the data to physicians, cancer researchers and pharmacologists in a format that is readily interpretable for clinical decision making. This review comprises a broad overview of these bioinformatics aspects and discusses the multiple analytical, technical and interpretational challenges that remain to efficiently translate molecular findings into personalized treatment recommendations.
Collapse
Affiliation(s)
- Natalie Jäger
- Hopp Children's Cancer Center Heidelberg (KiTZ) & Division of Pediatric Neurooncology, German Cancer Research Center (DKFZ), Heidelberg, Germany.
| |
Collapse
|
6
|
Wang X, Wang X, Ge P, Zhao X, Chen C, Hu S, Ren L. Establishment of improved review criteria for hematology analyzers in cancer hospitals. J Clin Lab Anal 2020; 35:e23638. [PMID: 33314392 PMCID: PMC7891522 DOI: 10.1002/jcla.23638] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2020] [Revised: 09/11/2020] [Accepted: 10/06/2020] [Indexed: 01/15/2023] Open
Abstract
BACKGROUND Although hematologic review criteria for general hospitals have been established, they may be insufficient for cancer hospitals. This study aimed to establish the appropriate review criteria for hematology analyzers in cancer hospitals. METHODS A total of 1003 samples from our hospital were randomly selected for blood smear preparation and microscopic review. The review criteria of the International Consensus Group for Hematology Review (ICGH) and Chinese consensus group were used to obtain the review, true-negative (TN), true-positive (TP), false-negative (FN), and false-positive (FP) rates, as well as the triggered rules. Our review criteria were established by comparing flag or numeric value information of TP and FP samples, adjusting rules to obtain better efficiency, a low slide review rate, and an acceptable FN rate. RESULTS Overall, 197 (19.64%) samples showed positive smear findings. Compared to the ICGH criteria, the slide review rate of the newly established criteria declined from 51.25% to 39.28%, and the TP and TN rates increased from 17.85% and 46.06% to 23.13% and 55.83%, respectively. The FN rate of the newly established criteria was 3.69%. Another set of samples used to validate the newly established criteria yielded the review, FN, and FP rates as 33.49%, 1.86%, and 25.58%, respectively. CONCLUSION The newly established review criteria for hematology analyzers enabled the prompt identification, smear, and further verification of doubtful specimens, without a significant increase in the workload, thus improving the efficiency of the review process. This study provided data support for other cancer hospitals to establish review criteria.
Collapse
Affiliation(s)
- Xiaoyan Wang
- Department of Clinical Laboratory, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| | - Xu Wang
- Department of Clinical Laboratory, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| | - Peng Ge
- Department of Clinical Laboratory, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| | - Xiaoqiang Zhao
- Department of Clinical Laboratory, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| | - Chong Chen
- Department of Clinical Laboratory, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| | - Shusheng Hu
- Department of Clinical Laboratory, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| | - Li Ren
- Department of Clinical Laboratory, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China
| |
Collapse
|
7
|
Baer C, Walter W, Hutter S, Twardziok S, Meggendorfer M, Kern W, Haferlach T, Haferlach C. "Somatic" and "pathogenic" - is the classification strategy applicable in times of large-scale sequencing? Haematologica 2019; 104:1515-1520. [PMID: 31273095 PMCID: PMC6669162 DOI: 10.3324/haematol.2019.218917] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2019] [Accepted: 05/15/2019] [Indexed: 12/20/2022] Open
|
8
|
Thierauf J, Ramamurthy N, Jo VY, Robinson H, Frazier RP, Gonzalez J, Pacula M, Dominguez Meneses E, Nose V, Nardi V, Dias-Santagata D, Le LP, Lin DT, Faquin WC, Wirth LJ, Hess J, Iafrate AJ, Lennerz JK. Clinically Integrated Molecular Diagnostics in Adenoid Cystic Carcinoma. Oncologist 2019; 24:1356-1367. [PMID: 30926674 PMCID: PMC6795155 DOI: 10.1634/theoncologist.2018-0515] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2018] [Accepted: 02/27/2019] [Indexed: 01/29/2023] Open
Abstract
Adenoid cystic carcinoma is a rare but aggressive type of salivary gland malignancy. This article addresses the need for more effective, biomarker‐informed therapies in rare cancers, focusing on clinical utility and financial sustainability of integrated next‐generation sequencing in routine practice. Background. Adenoid cystic carcinoma (ACC) is an aggressive salivary gland malignancy without effective systemic therapies. Delineation of molecular profiles in ACC has led to an increased number of biomarker‐stratified clinical trials; however, the clinical utility and U.S.‐centric financial sustainability of integrated next‐generation sequencing (NGS) in routine practice has, to our knowledge, not been assessed. Materials and Methods. In our practice, NGS genotyping was implemented at the discretion of the primary clinician. We combined NGS‐based mutation and fusion detection, with MYB break‐apart fluorescent in situ hybridization (FISH) and MYB immunohistochemistry. Utility was defined as the fraction of patients with tumors harboring alterations that are potentially amenable to targeted therapies. Financial sustainability was assessed using the fraction of global reimbursement. Results. Among 181 consecutive ACC cases (2011–2018), prospective genotyping was performed in 11% (n = 20/181; n = 8 nonresectable). Testing identified 5/20 (25%) NOTCH1 aberrations, 6/20 (30%) MYB‐NFIB fusions (all confirmed by FISH), and 2/20 (10%) MYBL1‐NFIB fusions. Overall, these three alterations (MYB/MYBL1/NOTCH1) made up 65% of patients, and this subset had a more aggressive course with significantly shorter progression‐free survival. In 75% (n = 6/8) of nonresectable patients, we detected potentially actionable alterations. Financial analysis of the global charges, including NGS codes, indicated 63% reimbursement, which is in line with national (U.S.‐based) and international levels of reimbursement. Conclusion. Prospective routine clinical genotyping in ACC can identify clinically relevant subsets of patients and is approaching financial sustainability. Demonstrating clinical utility and financial sustainability in an orphan disease (ACC) requires a multiyear and multidimensional program. Implications for Practice. Delineation of molecular profiles in adenoid cystic carcinoma (ACC) has been accomplished in the research setting; however, the ability to identify relevant patient subsets in clinical practice has not been assessed. This work presents an approach to perform integrated molecular genotyping of patients with ACC with nonresectable, recurrent, or systemic disease. It was determined that 75% of nonresectable patients harbor potentially actionable alterations and that 63% of charges are reimbursed. This report outlines that orphan diseases such as ACC require a multiyear, multidimensional program to demonstrate utility in clinical practice.
Collapse
Affiliation(s)
- Julia Thierauf
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
- Department of Otorhinolaryngology, Head and Neck Surgery, Heidelberg University Hospital, Heidelberg, Germany
| | - Nisha Ramamurthy
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Vickie Y Jo
- Department of Pathology, Brigham and Women's Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Hayley Robinson
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Ryan P Frazier
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Jonathan Gonzalez
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Maciej Pacula
- Department of Pathology, Computational Pathology, Boston, Massachusetts, USA
| | | | - Vania Nose
- Department of Pathology, Head and Neck Pathology, Boston, Massachusetts, USA
- Department of Pathology, Surgical Pathology, Boston, Massachusetts, USA
| | - Valentina Nardi
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Dora Dias-Santagata
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Long P Le
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
- Department of Pathology, Computational Pathology, Boston, Massachusetts, USA
| | - Derrick T Lin
- Department of Otolaryngology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - William C Faquin
- Department of Pathology, Surgical Pathology, Boston, Massachusetts, USA
- Department of Otolaryngology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - Lori J Wirth
- Cancer Center, Massachusetts General Hospital, Boston, Massachusetts, USA
- Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - Jochen Hess
- Department of Otorhinolaryngology, Head and Neck Surgery, Heidelberg University Hospital, Heidelberg, Germany
- Research Group Molecular Mechanisms of Head and Neck Tumors, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - A John Iafrate
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Jochen K Lennerz
- Department of Pathology, Center for Integrated Diagnostics, Massachusetts General Hospital/Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
9
|
Xu J, Yang P, Xue S, Sharma B, Sanchez-Martin M, Wang F, Beaty KA, Dehan E, Parikh B. Translating cancer genomics into precision medicine with artificial intelligence: applications, challenges and future perspectives. Hum Genet 2019; 138:109-124. [PMID: 30671672 PMCID: PMC6373233 DOI: 10.1007/s00439-019-01970-5] [Citation(s) in RCA: 95] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2018] [Accepted: 01/02/2019] [Indexed: 02/07/2023]
Abstract
In the field of cancer genomics, the broad availability of genetic information offered by next-generation sequencing technologies and rapid growth in biomedical publication has led to the advent of the big-data era. Integration of artificial intelligence (AI) approaches such as machine learning, deep learning, and natural language processing (NLP) to tackle the challenges of scalability and high dimensionality of data and to transform big data into clinically actionable knowledge is expanding and becoming the foundation of precision medicine. In this paper, we review the current status and future directions of AI application in cancer genomics within the context of workflows to integrate genomic analysis for precision cancer care. The existing solutions of AI and their limitations in cancer genetic testing and diagnostics such as variant calling and interpretation are critically analyzed. Publicly available tools or algorithms for key NLP technologies in the literature mining for evidence-based clinical recommendations are reviewed and compared. In addition, the present paper highlights the challenges to AI adoption in digital healthcare with regard to data requirements, algorithmic transparency, reproducibility, and real-world assessment, and discusses the importance of preparing patients and physicians for modern digitized healthcare. We believe that AI will remain the main driver to healthcare transformation toward precision medicine, yet the unprecedented challenges posed should be addressed to ensure safety and beneficial impact to healthcare.
Collapse
Affiliation(s)
- Jia Xu
- IBM Watson Health, Cambridge, MA, USA.
| | | | - Shang Xue
- IBM Watson Health, Cambridge, MA, USA
| | | | | | - Fang Wang
- IBM Watson Health, Cambridge, MA, USA
| | | | | | | |
Collapse
|