Augmented human intelligence (AHI) and artificial intelligence (AI) tools might shape the future of medical practice. The expansion of data generated by our systems, medical literature, and the inefficiencies of healthcare systems will necessitate utilizing the power of AI tools. 1,2 The integration of AHI tools into medical practice, including machine learning (ML) and deep learning algorithms, has begun. For instance, the United States food and drug administration (US-FDA) has approved many AI-based softwares since 2017 for medical use. 2,3 The introduction of digital pathology has brought many opportunities to the field of pathology, such as telemedicine. 4,5 Recently, the use of digital pathology has allowed for the use of ML (including deep learning algorithms) in the automation of pathological diagnosis. 6,7 The challenges facing the use of ML in pathology are many, including digitalizing slides, labeling in case of Abstract Machine learning (ML) offers opportunities to advance pathological diagnosis, especially with increasing trends in digitalizing microscopic images. Diagnosing leukemia is time-consuming and challenging in many areas globally and there is a growing trend in utilizing ML techniques for its diagnosis. In this review, we aimed to describe the literature of ML utilization in the diagnosis of the four common types of leukemia: acute lymphocytic leukemia (ALL), chronic lymphocytic leukemia (CLL), acute myeloid leukemia (AML), and chronic myelogenous leukemia (CML). Using a strict selection criterion, utilizing MeSH terminology and Boolean logic, an electronic search of MEDLINE and IEEE Xplore Digital Library was performed. The electronic search was complemented by handsearching of references of related studies and the top results of Google Scholar. The full texts of 58 articles were reviewed, out of which, 22 studies were included. The number of studies discussing ALL, AML, CLL, and CML was 12, 8, 3, and 1, respectively. No studies were prospectively applying algorithms in real-world scenarios. Majority of studies had small and homogenous samples and used supervised learning for classification tasks. 91% of the studies were performed after 2010, and 74% of the included studies applied ML algorithms to microscopic diagnosis of leukemia. The included studies illustrated the need to develop the field of ML research, including the transformation from solely designing algorithms to practically applying them clinically. K E Y W O R D S diagnosis, digital, leukemia, machine learning, pathology How to cite this article: Salah HT, Muhsen IN, Salama ME, Owaidah T, Hashmi SK. Machine learning applications in the diagnosis of leukemia: Current trends and future directions. Int J Lab Hematol. 2019;41:717-725. https ://doi.

Angioimmunoblastic T cell lymphoma (AITL) is a common subtype of mature peripheral T cell lymphoma (PTCL). As per the 2016 World Health Organization classification, AITL is now considered as a subtype of nodal T cell lymphoma with follicular helper T cells. The diagnosis is challenging and requires a constellation of clinical, laboratory and histopathological findings. Significant progress in the molecular pathophysiology of AITL has been achieved in the past two decades. Characteristic genomic features have been recognized that could provide a potential platform for better diagnosis and future prognostic models. Frontline therapy for AITL was mainly depending on chemotherapy and the management of relapsed or refractory AITL is still unsatisfactory with a very poor prognosis. Upfront transplantation offers better survival. Novel agents have been introduced recently with promising outcomes. Several clinical trials of combinations using novel agents are underway. Herein, we briefly review recent advances in AITL diagnosis and the evolving treatment landscape.

Acute promyelocytic leukemia (APL) is a special disease entity of acute myeloid leukemia (AML). The clinical use of all-trans retinoic acid (ATRA) has transformed APL into the most curable form of AML. The majority of APL cases are characterized by the fusion gene PML-RARA. Although the PML-RARA fusion gene can be detected in almost all APL cases, translocation variants of APL have been reported. To date, this is the most comprehensive review of these translocations, discussing 15 different variants. Reviewed genes involved in APL variants include: ZBTB16, NPM, NuMA, STAT5b, PRKAR1A, FIP1L1, BCOR, NABP1, TBLR1, GTF2I, IRF2BP2, FNDC3B, ADAMDTS17, STAT3, and TFG. The genotypic and phenotypic features of APL translocations are summarized. All reported studies were either case reports or case series indicating the rarity of these entities and limiting the ability to drive conclusions regarding their characteristics. However, reported variants have shown variable clinical and morphological features, with diverse responsiveness to ATRA.

Supplemental Digital Content is available in the text.

Subsequent malignancies are well-documented complications in long-term follow-up of cancer patients. Recently, genetically modified immune effector cells (IECs) have showed benefit in hematologic malignancies and are being evaluated in clinical trials for solid tumors. While the short-term complications of IECs are well described, there is limited literature summarizing long-term follow-up, including subsequent malignancies. We retrospectively reviewed data from 340 patients treated across 27 investigator-initiated pediatric and adult clinical trials at our center. All patients received IECs genetically modified with gamma-retroviral vectors to treat relapsed and/or refractory hematologic or solid malignancies. In a cumulative 1,027 years of long-term follow-up, 13 patients (3.8%) developed another cancer with a total of 16 events (four hematologic malignancies and 12 solid tumors). The 5-year cumulative incidence of a first subsequent malignancy in the recipients of genetically modified IECs was 3.6% (95% CI: 1.8%-6.4%). For 11 of the 16 subsequent tumors, biopsies were available, and no sample was transgene positive by PCR. Replication competent retrovirus testing of peripheral blood mononuclear cells was negative in the 13 patients with subsequent malignancies tested. Rates of subsequent malignancy were low and comparable to standard chemotherapy. These results suggest that the administration of IECs genetically modified with gamma retroviral vectors does not increase the risk for subsequent malignancy.