The CLI-NLP algorithm for identification of CLI from narrative clinical notes in an EHR had excellent PPV and has potential for translation to patient care as it will enable automated identification of CLI cases for quality projects, clinical decision support tools and support a learning healthcare system.

PURPOSE The advancement of natural language processing (NLP) has promoted the use of detailed textual data in electronic health records (EHRs) to support cancer research and to facilitate patient care. In this review, we aim to assess EHR for cancer research and patient care by using the Minimal Common Oncology Data Elements (mCODE), which is a community-driven effort to define a minimal set of data elements for cancer research and practice. Specifically, we aim to assess the alignment of NLP-extracted data elements with mCODE and review existing NLP methodologies for extracting said data elements. METHODS Published literature studies were searched to retrieve cancer-related NLP articles that were written in English and published between January 2010 and September 2020 from main literature databases. After the retrieval, articles with EHRs as the data source were manually identified. A charting form was developed for relevant study analysis and used to categorize data including four main topics: metadata, EHR data and targeted cancer types, NLP methodology, and oncology data elements and standards. RESULTS A total of 123 publications were selected finally and included in our analysis. We found that cancer research and patient care require some data elements beyond mCODE as expected. Transparency and reproductivity are not sufficient in NLP methods, and inconsistency in NLP evaluation exists. CONCLUSION We conducted a comprehensive review of cancer NLP for research and patient care using EHRs data. Issues and barriers for wide adoption of cancer NLP were identified and discussed.

In vitro antifungal susceptibility of 32 clinical and environmental Talaromyces marneffei isolates recovered from southern China was performed against olorofim and 7 other systemic antifungals including: amphotericin B, 5-flucytosine, posaconazole, voriconazole, caspofungin and terbinafine using the CLSI methodology. In comparison, olorofim was the most active antifungal agent against both mold and yeast phases of all tested Talaromyces marneffei isolates, exhibiting an MIC range, MIC50, and MIC90 of 0.0005-0.002 μg/ml, 0.0005 μg/ml, and 0.0005 μg/ml, respectively.

Chromoblastomycosis is a chronic fungal infection of the skin and subcutaneous tissue. The most common etiologic agent encountered in Southern China is from the genus Fonsecaea. Fonsecaea species are often misidentified due to indistinct morphology features; furthermore, recent taxonomy revision was done on the fungi genus. Herein, a comprehensive evaluation with molecular sequencing data based on internal transcribed spacer (ITS) ribosomal DNA regions as molecular targets were implemented to 37 clinical isolates from chromoblastomycosis patients. Twenty strains that were formerly identified as Fonsecaea pedrosoi through morphological characteristic were verified to be either Fonsecaea nubica or Fonsecaea monophora, while 17 strains were appropriately identified as F. monophora. A phylogenetic method was further performed to establish the species delimitation. Our investigations validate that the clinical isolates from Guangdong consist of F. monophora and the recently found new species, F. nubica. In this study, F. pedrosoi has not been isolated from chromoblastomycosis patients in Guangdong, Southern China. Reevaluation of previous reports regarding F. pedrosoi as chromoblastomycosis etiologic agent in China is necessary for a comprehensive assessment of geographic distribution pattern of Fonsecaea species. This study is the first reported study presenting large samples of F. nubica domestic or abroad.