A B S T R A C T PurposeAllogeneic hematopoietic stem-cell transplantation (HSCT) is potentially curative for acute leukemia (AL), but carries considerable risk. Machine learning algorithms, which are part of the data mining (DM) approach, may serve for transplantation-related mortality risk prediction. Patients and MethodsThis work is a retrospective DM study on a cohort of 28,236 adult HSCT recipients from the AL registry of the European Group for Blood and Marrow Transplantation. The primary objective was prediction of overall mortality (OM) at 100 days after HSCT. Secondary objectives were estimation of nonrelapse mortality, leukemia-free survival, and overall survival at 2 years. Donor, recipient, and procedural characteristics were analyzed. The alternating decision tree machine learning algorithm was applied for model development on 70% of the data set and validated on the remaining data. ResultsOM prevalence at day 100 was 13.9% (n ϭ 3,936). Of the 20 variables considered, 10 were selected by the model for OM prediction, and several interactions were discovered. By using a logistic transformation function, the crude score was transformed into individual probabilities for 100-day OM (range, 3% to 68%). The model's discrimination for the primary objective performed better than the European Group for Blood and Marrow Transplantation score (area under the receiver operating characteristics curve, 0.701 v 0.646; P Ͻ .001). Calibration was excellent. Scores assigned were also predictive of secondary objectives. ConclusionThe alternating decision tree model provides a robust tool for risk evaluation of patients with AL before HSCT, and is available online (http://bioinfo.lnx.biu.ac.il/ϳbondi/web1.html). It is presented as a continuous probabilistic score for the prediction of day 100 OM, extending prediction to 2 years. The DM method has proved useful for clinical prediction in HSCT.

Numerous studies have been published regarding outcomes of cancer patients infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus causing the coronavirus disease 2019 (COVID-19) infection. However, most of these are single-center studies with a limited number of patients. To better assess the outcomes of this new infection in this subgroup of susceptible patients, we performed a systematic review and meta-analysis to evaluate the impact of COVID-19 infection on cancer patients. We performed a literature search using PubMed, Web of Science, and Scopus for studies that reported the risk of infection and complications of COVID-19 in cancer patients and retrieved 22 studies (1018 cancer patients). The analysis showed that the frequency of cancer among patients with confirmed COVID-19 was 2.1% (95% confidence interval [CI]: 1.3–3) in the overall cohort. These patients had a mortality of 21.1% (95% CI: 14.7–27.6), severe/critical disease rate of 45.4% (95% CI: 37.4–53.3), intensive care unit (ICU) admission rate of 14.5% (95% CI: 8.5–20.4), and mechanical ventilation rate of 11.7% (95% CI: 5.5–18). The double-arm analysis showed that cancer patients had a higher risk of mortality (odds ratio [OR] = 3.23, 95% CI: 1.71–6.13), severe/critical disease (OR = 3.91, 95% CI: 2.70–5.67), ICU admission (OR = 3.10, 95% CI: 1.85–5.17), and mechanical ventilation (OR = 4.86, 95% CI: 1.27–18.65) than non-cancer patients. Furthermore, cancer patients had significantly lower platelet levels and higher D-dimer levels, C-reactive protein levels, and prothrombin time. In conclusion, these results indicate that cancer patients are at a higher risk of COVID-19 infection-related complications. Therefore, cancer patients need diligent preventive care measures and aggressive surveillance for earlier detection of COVID-19 infection.

Multiple myeloma (MM) is a heterogeneous hematologic malignancy involving the proliferation of plasma cells derived by different genetic events contributing to the development, progression, and prognosis of this disease. Despite improvement in treatment strategies of MM over the last decade, the disease remains incurable. All efforts are currently focused on understanding the prognostic markers of the disease hoping to incorporate the new therapeutic modalities to convert the disease into curable one. We present this comprehensive review to summarize the current standard prognostic markers used in MM along with novel techniques that are still in development and highlight their implications in current clinical practice.