Search

AIM To evaluate the role that artificial intelligence (AI) could play in assisting radiologists as the first reader of chest radiographs (CXRs), to increase the accuracy and efficiency of lung cancer diagnosis by flagging positive cases before passing the remaining examinations to standard reporting. MATERIALS AND METHODS A dataset of 400 CXRs including 200 difficult lung cancer cases was curated. Examinations were reviewed by three FRCR radiologists and an AI algorithm to establish performance in tumour identification. AI and radiologist labels were combined retrospectively to simulate the proposed AI triage workflow. RESULTS When used as a standalone algorithm, AI classification was equivalent to the average radiologist performance. The best overall performances were achieved when AI was combined with radiologists, with an average reduction of missed cancers of 60%. Combination with AI also standardised the performance of radiologists. The greatest improvements were observed when common sources of errors were present, such as distracting findings. DISCUSSION The proposed AI implementation pathway stands to reduce radiologist errors and improve clinician reporting performance. Furthermore, taking a radiologist-centric approach in the development of clinical AI holds promise for catching systematically missed lung cancers. This represents a tremendous opportunity to improve patient outcomes for lung cancer diagnosis.

On February 3, 2015, the FDA granted accelerated approval to palbociclib (IBRANCE, Pfizer Inc.), an inhibitor of cyclin-dependent kinases 4 and 6 (CDK4 and CDK6), for use in combination with letrozole for the treatment of postmenopausal women with estrogen receptor (ER)–positive, HER2-negative advanced breast cancer as initial endocrine-based therapy for their metastatic disease. The approval is based on a randomized, multicenter, open-label phase I/II trial (PALOMA-1) in 165 patients randomized to palbociclib (125 mg orally daily for 21 consecutive days, followed by 7 days off treatment) plus letrozole (2.5 mg orally daily) or letrozole alone. The phase II portion of the trial was divided into two cohorts: cohort 1 enrolled 66 biomarker-unselected patients and cohort 2 enrolled 99 biomarker-positive patients. The major efficacy outcome measure was investigator-assessed progression-free survival (PFS). A large magnitude of improvement in PFS was observed in patients receiving palbociclib plus letrozole compared with patients receiving letrozole alone (HR, 0.488; 95% confidence interval, 0.319–0.748). Multiple sensitivity analyses were supportive of clinical benefit. The most common adverse reaction in patients receiving palbociclib plus letrozole was neutropenia. This article summarizes the FDA thought process and data supporting accelerated approval based on PALOMA-1 that may be contingent upon verification and description of clinical benefit in the ongoing and fully accrued confirmatory trial PALOMA-2. Clin Cancer Res; 21(21); 4760–6. ©2015 AACR.

Human granulocytic ehrlichiosis (HGE) is an emerging tick-borne disease recently recognized in the United States. The blacklegged tick, Ixodes scapularis Say, is the principle vector in the eastern United States. The disease has been commonly reported in the northeastern and upper midwestern states; however, suitable vectors and reservoir hosts exist in the southeast. To assay the prevalence of the HGE agent in vector ticks, we screened 818 individual I. scapularis from 15 locations in South Carolina, Georgia, and Florida using nested polymerase chain reaction, which targets the HGE agent 16S rRNA gene. Prevalence among locations ranged from 0 to 20%. The overall average prevalence of 15 sites was 1.6% (n = 818). Verification by sequencing the 16S rDNA from the positive samples showed 99.8-100% nucleotide identities with the sequences of the HGE agent in GenBank. These results were supported by the phylogenetic analysis using 16S rDNA sequences.