Significant clinical response to JAK1/2 inhibition in a patient with CSF3R-T618I-positive atypical chronic myeloid leukemia.

Mutations in CSF3R (colony-stimulating factor 3 receptor) are frequent oncogenic drivers in chronic neutrophilic leukemia (CNL) and atypical chronic myeloid leukemia (aCML). Here we describe a 75 year old man who was diagnosed with CSF3R-T618I-positive atypical CML. He presented with leukocytosis, anemia, and thrombocytopenia and developed massive splenomegaly and severe constitutional symptoms. Hydroxyurea was given over a 6 month period but failed to provide any measureable clinical benefit. Eventually, he was treated with ruxolitinib, an FDA-approved JAK1/2 inhibitor, which resulted in dramatic improvement of his blood counts. He also had significant reduction of spleen volume and constitutional symptoms. This case highlights the need for a clinical trial to interrogate JAK1/2 as a potential molecular target in CNL and aCML in patients with or without CSF3R mutation. A clinical trial evaluating the safety and efficacy of ruxolitinib for this patient population is registered at ClinicalTrials.gov (NCT02092324).

Building an automated problem list based on natural language processing: lessons learned in the early phase of development.

Detailed problem lists that comply with JCAHO requirements are important components of electronic health records. Besides improving continuity of care electronic problem lists could serve as foundation infrastructure for clinical trial recruitment, research, biosurveillance and billing informatics modules. However, physicians rarely maintain problem lists. Our team is building a system using MetaMap and UMLS to automatically populate the problem list. We report our early results evaluating the application. Three physicians generated gold standard problem lists for 100 cardiology ambulatory progress notes. Our application had 88% sensitivity and 66% precision using a non-modified UMLS dataset. The systemâs misses concentrated in the group of ambiguous problem list entries (Chi-square=27.12 p<0.0001). In addition to the explicit entries, the notes included 10% implicit entry candidates. MetaMap and UMLS are readily applicable to automate the problem list. Ambiguity in medical documents has consequences for performance evaluation of automated systems.

Natural language processing of clinical trial announcements: exploratory-study of building an automated screening application.

Clinical trials are important for the advancement of medical research. Despite of the benefits clinical trial enrollment is low. We study the feasibility of using NLP to assist with automatic eligibility screening by extracting medical diagnoses from the inclusion and exclusion criteria of cancer clinical trial announcements posted on the internet. We compare the performances of the system versus an oncologist.

A pilot study of low-dose thalidomide and interferon alpha-2b in patients with metastatic melanoma who failed prior treatment.

Melanoma is a hypervascular tumor and angiogenesis plays a critical role in the development/progression of metastases. As various pathways are involved in tumor angiogenesis, a combination of agents with different antiangiogenesis activities is a reasonable approach. To determine the efficacy and toxicity of combination treatment with low-dose thalidomide and low-dose interferon (IFN) in patients with stage IV melanoma who failed prior treatment(s), fifteen patients with metastatic melanoma (nine cutaneous, six uveal) received oral thalidomide (200 mg daily) with subcutaneous interferon (IFN)-alpha2b (3 MIU, 3x/week). Stabilization or regression of metastases (as evidenced by computed tomographic measurement) was the primary endpoint of the study. Patients were evaluated monthly for toxicity and every 2 months for clinical response. At a median follow-up of 22.8 months (range, 12-32 months), one patient with metastatic cutaneous melanoma achieved partial response, three patients achieved stable disease (one uveal, two cutaneous), nine patients progressed, and two were not evaluable. The time to progression was 6 months for the patient with partial response, and 2, 5.5+ and 11 months for three patients with stable disease. The estimated median overall survival was 4.7 months (confidence interval, 2.2-9.9 months; range, 0.9-31.5 months), and median progression-free survival was 1.8 months (confidence interval, 1.5-3.0 months; range, 0.5-14 months). Grade 3 toxicities related to treatment included neutropenia (n=5), elevation of transaminases (n=2), and neuropathy (n=1). No treatment-related deaths were experienced. Thalidomide+IFN is a safe and tolerable palliative treatment for previously treated stage IV melanoma.