Search

Abstract: Acute graft-versus-host disease (aGVHD) is 1 of the critical complications that often occurs following allogeneic hematopoietic stem cell transplantation (HSCT). Thus far, various types of prediction scores have been created using statistical calculations. The primary objective of this study was to establish and validate the machine learning–dependent index for predicting aGVHD. This was a retrospective cohort study that involved analyzing databases of adult HSCT patients in Japan. The alternating decision tree (ADTree) machine learning algorithm was applied to develop models using the training cohort (70%). The ADTree algorithm was confirmed using the hazard model on data from the validation cohort (30%). Data from 26 695 HSCT patients transplanted from allogeneic donors between 1992 and 2016 were included in this study. The cumulative incidence of aGVHD was 42.8%. Of >40 variables considered, 15 were adapted into a model for aGVHD prediction. The model was tested in the validation cohort, and the incidence of aGVHD was clearly stratified according to the categorized ADTree scores; the cumulative incidence of aGVHD was 29.0% for low risk and 58.7% for high risk (hazard ratio, 2.57). Predicting scores for aGVHD also demonstrated the link between the risk of development aGVHD and overall survival after HSCT. The machine learning algorithms produced clinically reasonable and robust risk stratification scores. The relatively high reproducibility and low impacts from the interactions among the variables indicate that the ADTree algorithm, along with the other data-mining approaches, may provide tools for establishing risk score.

Abstract: To characterize the outcomes of patients who developed a particular subsequent solid cancer after hematopoietic cell transplantation (HCT), age at cancer diagnosis, survival, and causes of death were compared with the respective primary cancer in the general population, using data from the national HCT registry and population-based cancer registries in Japan. Among 31 867 patients who underwent a first HCT between 1990 and 2013 and had progression-free survival at 1 year, 713 patients developed subsequent solid cancer. The median age at subsequent solid cancer diagnosis was 55 years, which was significantly younger than the 67 years for primary cancer patients in the general population (P < .001). The overall survival probability was 60% at 3 years after diagnosis of subsequent solid cancer and differed according to cancer type. Development of most solid cancers was associated with an increased risk of subsequent mortality after HCT. Subsequent solid cancers accounted for 76% of causes of death. Overall survival probabilities adjusted for age, sex, and year of diagnosis were lower in the HCT population than in the general population for colon, bone/soft tissue, and central nervous system cancers and did not differ statistically for other cancers. In conclusion, most subsequent solid cancers occurred at younger ages than primary cancers, emphasizing the need for cancer screening at younger ages. Subsequent solid cancers showed similar or worse survival compared with primary cancers. Biological and genetic differences between primary and subsequent solid cancers remain to be determined.

A 54-year-old woman with acute myeloid leukemia (AML) achieved complete remission by induction chemotherapy, but developed zygomycosis after consolidation therapy. As zygomycosis could not be cured by liposomal amphotericin B and micafungin, left lower lobectomy was performed. As AML relapsed 7 months after onset, she received haploidentical stem cell transplantation under administration of liposomal amphotericin B. Despite experiencing severe acute graft-versus-host disease, she remains alive with no relapse of either zygomycosis or AML. Keywords: Zygomycosis, Acute myeloid leukemia, Liposomal amphotericin B, Stem cell transplantation

We present the case of a 79-year-old man who showed multiple pulmonary nodules on chest computed tomography (CT) after being treated for 6 months with ruxolitinib, an inhibitor of Janus kinase (JAK) 1 and 2, to treat primary myelofibrosis. We examined the lesions by bronchoscopy, and the biopsy specimen revealed fungus bodies of Cryptococcus with granulomatous inflammation. As a result, the patient was diagnosed with pulmonary cryptococcosis. The patient was treated with fluconazole (200 mg daily for 2 weeks) with concomitant ruxolitinib administration, but the pulmonary lesions progressed. Subsequently, the patient was treated with voriconazole (300 mg daily for 3 weeks), but the lesions worsened further. The administration of ruxolitinib was therefore discontinued, and the dosage of voriconazole was increased to 400 mg daily. Three months later, the pulmonary lesions diminished in size. The present case of pulmonary cryptococcosis occurred in a patient treated with ruxolitinib. Treatment of pulmonary cryptococcosis with concomitant JAK inhibitor administration may result in poor treatment efficacy. It might be better to stop administration of JAK inhibitors, if possible, in patients being treated for pulmonary cryptococcosis.