Background: Cognitive impairment after BMT for hematologic malignancies typically involves processing speed, attention and working memory. Survivors perceive these deficits as learning and/or memory problems. However, limited information exists regarding learning/memory problems experienced by survivors several years after BMT. We addressed this gap using the BMTSS. Methods: BMTSS is a retrospective cohort study examining long-term outcomes of individuals who survived ≥2y after BMT performed between 1974 and 2014 at three transplant centers. Study participants completed a 255-item questionnaire covering diagnosis by a healthcare provider of health conditions (including learning/memory problems), sociodemographic characteristics, and functional status. We used a nested matched case-control study design. Cases consisted of individuals with learning/memory problems developing after BMT (n = 543). Each case was matched to a BMTSS participant without memory problems (controls: n = 543) using the following criteria: cancer diagnosis, race/ethnicity, type of BMT (allogeneic or autologous), and time from BMT. Multivariable conditional logistic regression analysis was used to identify clinical factors (age at BMT, stem cell source, chronic graft vs. host disease [cGvHD], total body irradiation [TBI], fatigue, pain) and demographic factors (household income, education, sex) associated with learning/memory problems. We also examined the association between learning/memory problems and instrumental activities of daily living (IADL). Analyses were stratified by type of BMT. Results: For all survivors (n = 1,086), mean age at BMT was 40.7y and at study participation was 53.3y (18-85); 47% of the study population was females; 78% were non-Hispanic whites; 31% reported an annual household income < $50k. Primary diagnoses included leukemia (50%), lymphoma (36%), and other (14%); 55% received an allogeneic BMT (36% developed cGvHD); 54% received TBI; and 68% received peripheral blood stem cells. Allogeneic BMT survivors with fatigue (odds ratio [OR] = 2.2, 95% CI, 1.4-3.3; p = 0.001), significant pain (OR = 1.8, 95% CI, 1.1-2.9; p = 0.02) and < college education (OR = 1.6, 95% CI, 1.1-2.5; p = 0.02) had higher odds of reporting learning/memory problems. Autologous BMT survivors exposed to TBI (OR = 2.8, 95% CI, 1.4-5.4; p = 0.003) and reporting significant pain (OR = 1.7, 95% CI, 1.0-2.9; p = 0.05) had higher odds of reporting learning/memory problems. Learning/memory problems were associated with increased odds of impairments in IADL in both autologous (OR = 2.1, 95% CI, 1.1-4.0; p = 0.03) and allogeneic (OR = 2.0, 95% CI, 1.2-3.3; p = 0.01) BMT survivors. Conclusions: Modifiable risk factors, such as fatigue and pain, can be targeted to mitigate the learning/memory problems and improve the functional outcomes of BMT survivors.