The evidence-based literature on healthcare is currently expanding exponentially. The opportunities provided by the advancement in artificial intelligence (AI) tools such as machine learning are appealing in tackling many of the current healthcare challenges. Thus, AI integration is expanding in most fields of healthcare, including the field of hematology. This study aims to review the current applications of AI in the field of hematopoietic cell transplantation (HCT). A literature search was done involving the following databases: Ovid MEDLINE, including In-Process and other non-indexed citations, and Google Scholar. The abstracts of the following professional societies were also screened: American Society of Hematology, American Society for Blood and Marrow Transplantation, and European Society for Blood and Marrow Transplantation. The literature review showed that the integration of AI in the field of HCT has grown remarkably in the last decade and offers promising avenues in diagnosis and prognosis in HCT populations targeting both pre- and post-transplant challenges. Studies of AI integration in HCT have many limitations that include poorly tested algorithms, lack of generalizability, and limited use of different AI tools. Machine learning techniques in HCT are an intense area of research that needs much development and extensive support from hematology and HCT societies and organizations globally as we believe that this will be the future practice paradigm.

Objective: This study aimed to evaluate DNMT3A exon 23 mutations and their prognostic impacts in the presence of NPM1 and FLT3 mutations in acute myeloid leukemia (AML) patients who underwent allogeneic hematopoietic stem cell transplantation (HSCT).
Materials and Methods: This study comprised 128 adult AML patients referred to the Hematology-Oncology and Stem Cell Research Center of Shariati Hospital. NPM1 and FLT3-ITD mutations were detected by fragment analysis. For DNMT3A exon 23 mutation analysis, we used Sanger sequencing. Overall survival (OS) and relapse-free survival (RFS) curves were estimated by the Kaplan-Meier method and the logrank test was used to calculate differences between groups.
Results: The prevalence of DNMT3A exon 23 mutations was 15.6% and hotspot region R882 mutations were prominent. RFS and OS were compared in patients with and without DNMT3A exon 23 mutations using univariate analysis and there was no significant difference between these groups of patients. On the contrary, the FLT3-ITD mutation significantly reduced the OS (p=0.009) and RFS (p=0.006) in AML patients after allogeneic HSCT. In the next step, patients with AML were divided into four groups regarding FLT3-ITD and DNMT3A mutations. Patients with DNMT3A R882mut/FLT3-ITDpos had the worst OS and RFS. These results indicate that DNMT3A mutations alone do not affect the clinical outcomes of AML patients undergoing allogeneic HSCT, but when accompanied by FLT3-ITD mutations, the OS was significantly reduced (5-year OS 0% for DNMT3A R882mut/FLT3-ITDpos patients vs. 62% DNMT3A R882wt/FLT3-ITDneg, p=0.025) and the relapse rate increased.
Conclusion: It can be deduced that DNMT3A R882mut/FLT3-ITDpos is an unfavorable prognostic factor in AML patients even after allogeneic HSCT.

Objective: Traditional prognostic factors have proved insufficient to account for heterogeneity in the clinical behavior of chronic lymphocytic leukemia (CLL). Cryptochrome-1 (CRY-1) is a circadian clock gene essential in maintaining the circadian rhythm and regulating cell proliferation. We evaluated CRY-1 gene expression in CLL and addressed its putative role as a prognostic indicator for the clinical course of CLL.
Materials and Methods: A total of 100 CLL patients at diagnosis were studied for CRY-1 gene expression by real-time reverse-transcription polymerase chain reaction and were followed for assessment of time to first treatment (TFT).
Results: CRY-1 was expressed in 94% of the CLL patients at diagnosis. The median CRY-1 relative gene expression level (0.006) stratified patients into high and low expression groups. Forty of 100 (40%) CLL patients showed high CRY-1, 54/100 (54%) showed low CRY- 1, and 6/100 (6%) had undetectable CRY-1 gene expression. High CRY- 1 gene expression was concordant with CD38+, Zap-70+, and double CD38+Zap-70+ expression; unfavorable/intermediate cytogenetics; unmutated immunoglobulin heavy-chain variable-region gene; and diffuse marrow infiltration. The high CRY-1 gene expression patient group exhibited shorter TFT than the patients with low CRY-1 gene expression. A Cox proportional hazard regression model identified CRY- 1 gene expression to be independently predictive for TFT.
Conclusion: CRY-1 is differentially expressed among CLL patients, stratifying them into low-risk and high-risk groups. CRY-1 gene expression could constitute a reliable prognostic indicator for CLL progression, complementing the role of standard well-established prognostic factors. CRY-1 gene expression could be employed as a prognostic indicator for disease progression during the initial prognostic work-up and follow-up for CLL patients.

Objective: The aim of this study was to evaluate the relation between the rate of fluorine-18 (18F) fludeoxyglucose (FDG) uptake and CD38 and CD138 expression in myeloma cells in bone marrow and other clinical parameters in patients with multiple myeloma (MM).
Materials and Methods: Patients with the diagnosis of MM who underwent 18F-FDG positron emission tomography/computed tomography (PET/CT) for initial staging were evaluated retrospectively. We analyzed a total of 42 patients (43-83 years old, mean: 64.4±9.9). Hematological and biochemical tests including hemoglobin, hematocrit, C-reactive protein, β2-microglobulin, creatinine, albumin, calcium, lactate dehydrogenase, and erythrocyte sedimentation rate were recorded. In bone marrow samples, plasma cell ratio and CD38 and CD138 immunohistochemical staining were evaluated. On PET/ CT images, mean standardized uptake values (SUVmean) of the right anterior and posterior iliac crest and right proximal femora were calculated. The correlations between the average SUVmean of bone marrow and CD38- and CD138-expressing myeloma cells and other parameters were analyzed by Spearman’s correlation test. Values of p<0.05 were considered statistically significant.
Results: Types of MM were IgGK (45%), IgGL (21%), IgAK (7%), IgAL (10%), and others (17%). Thirty-two (76%) patients were at stage III according to the Salmon-Durie staging system. There was a statistically significant positive correlation between bone marrow FDG uptake and percentage of plasma cells in bone marrow and CD38 and CD138 expression in plasma cells (r=0.403, r=0.339, and r=0.409) and β2-microglobulin and C-reactive protein levels (r=0.676, r=0.541). There was a negative correlation between bone marrow FDG uptake and hemoglobin and hematocrit values (r=-0.377 and r=-0.368). Other hematological parameters were not correlated with FDG uptake in bone marrow.
Conclusion: Increased FDG uptake is correlated with the percentage of CD38 and CD138 expression in plasma cells in bone marrow. In addition to initial staging, 18F-FDG PET/CT is useful in treatment planning and prognostic evaluation in MM patients.

Objective: Useful prognostic biomarkers for diffuse large B-cell lymphoma (DLBCL) patients have been reported. To determine the prognostic value of hemoglobin (Hb) level in DLBCL patients, we performed a retrospective study.
Materials and Methods: We evaluated disease outcome, progressionfree survival (PFS), overall survival as the endpoint, and clinical and laboratory factors affecting the outcome of 185 DLBCL patients who had received rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisolone therapy during 2004-2014.
Results: The study group included 121 men and 64 women with a median age of 66 years minimum-maximum: 21-83 years. In univariate analysis, factors independently associated with worse PFS were Eastern Cooperative Oncology Group performance status ≥2, Ann Arbor stage III or IV, anemia with Hb levels of <10 g/dL, and serum albumin of <3.5 g/ dL. In multivariate analysis, anemia with Hb levels of <10 g/dL and Ann Arbor stage III or IV were found to be international index-independent prognostic factors (hazard ratio: 2.4; p=0.04).
Conclusion: Anemia is an independent prognostic marker of poor outcome in DLBCL patients. Hb can be an easily available prognostic marker for risk stratification in these patients.

Objective: Hemorrhage is the leading cause of injury-related prehospital mortality. We investigated worst-case scenarios and possible requirements of the Turkish military. As we plan to use blood resources during casualty transport, the impact of transport-related mechanical stress on packed red blood cells (PRBCs) was analyzed.
Materials and Methods: The in vitro experiment was performed in the environmental test laboratories of ASELSAN®. Operational vibrations of potential casualty transport mediums such as Sikorsky helicopters, Kirpi® armored vehicles, and the NATO vibration standard MIL-STD- 810G software program were recorded. The most powerful mechanical stress, which was created by the NATO standard, was applied to 15 units of fresh (≤7 days) and 10 units of old (>7 days) PRBCs in a blood cooler box. The vibrations were simulated with a TDS v895 Medium- Force Shaker Device. On-site blood samples were analyzed at 0, 6, and 24 h for biochemical and biomechanical analyses.
Results: The mean (±standard deviation) age of fresh and old PRBCs was 4.9±2.2 and 32.8±11.8 days, respectively. Six-hour mechanical damage of fresh PRBCs was demonstrated by increased erythrocyte fragmentation rates (p=0.015), hemolysis rates (p=0.003), and supernatant potassium levels (p=0.003) and decreased hematocrit levels (p=0.015). Old PRBC hemolysis rates (p=0.015), supernatant potassium levels (p=0.015), and supernatant hemoglobin (p=0.015) were increased and hematocrit levels were decreased (p=0.015) within 6 h. Two (13%) units of fresh PRBCs and none of the old PRBCs were eligible for transfusion after 6 h of mechanical stress.
Conclusion: When an austere combat environment was simulated for 24 h, fresh and old PRBC hemolysis rates were above the quality criteria. Currently, the technology to overcome this mechanical damage does not seem to exist. In light of the above data, a new national project is being performed.

Objective: We assessed the effect of anemia on cardiovascular findings in obese adolescents.
Materials and Methods: We studied 29 anemic and 33 nonanemic obese adolescents, and 33 nonobese healthy adolescents. These three groups were investigated for clinical and laboratory features of anemia and obesity. Echocardiography was used to examine cardiac functions. Results: The anemia was mild (mean hemoglobin: 11.67±0.79 g/dL), ferritin level was significantly low, and C-reactive protein and fibrinogen levels were significantly high in anemic obese patients. Increased cardiac pulse and echocardiographic findings, which may be indicative of early left ventricular diastolic dysfunction, were present in these patients.
Conclusion: Anemia may develop due to iron deficiency and chronic inflammation in obese adolescents. Even mild anemia may cause increased heart rate and affect left ventricular diastolic functions. Diet programs for obese children should be carefully planned to avoid iron deficiency anemia, which may worsen the cardiac events in longterm follow-up.