In The American journal of pathology ; h5-index 54.0
Diagnosis and classification of tumors is increasingly dependent on biomarkers. RNA expression profiling using next-generation sequencing (NGS) provides reliable and reproducible information on the biology of cancer. This study investigated targeted transcriptome and artificial intelligence) for differential diagnosis of hematologic and solid tumors. RNA from hematologic neoplasms (N=2606), solid tumors (N=2038), normal bone marrow (BM) (N=782), and lymph node control (N=24) were sequenced using NGS using a targeted 1408-gene panel. There were 20 subtypes of hematologic neoplasms and 24 subtypes of solid tumors. Machine learning was used for diagnosis between two classes. Geometric mean naïve Bayesian (GMNB) classifier was used for differential diagnosis across 45 diagnostic entities with assigned rankings. Machine learning showed high accuracy in distinguishing between two diagnoses, with area under the curve varying between 1 and 0.841. GMNB algorithm was trained using 3045 samples and tested on 1415 samples, and showed correct first-choice diagnosis in 100%, 88%, 85 %, 82 %, 88 %, 72 %, and 72% of ALL, AML, DLBCL, colorectal cancer, lung cancer, CLL, and follicular lymphoma cases, respectively. We conclude that targeted transcriptome combined with AI are highly useful for diagnosis and classification of various cancers. Mutation profiles and clinical information can improve these algorithms and minimize errors in diagnoses.
Zhang Hong, Qureshi Muhammad Asif, Wahid Mohsin, Charifa Ahmad, Ehsan Amir, Ip Andrew, De Dios Ivan, Ma Wanlong, Sharma Ipsa, McCloskey James, Donato Michele, Siegel David, Gutierrez Martin, Pecora Andrew, Goy Andre, Albitar Maher