Clinical NLP and ML Research

While still a very young area of research, clinical NLP has become one of the most popular areas of research due to the social benefits of applications that leverage NLP techniques. Below I summarize the latest research and stories related to clinical NLP.

→ A paper presents an NLP-method to combine disparate resources and acquire accurate information about health providers.

→ Rule based NLP system found to be better than ML based NLP system on clinical reports for teaching machines to read radiology report.

→ Radiology has recently seen significant gains in the use of deep learning methods for things like action recognition and automatic detection of brain injuries or skull fractures. AI researcher, Sasank Chilamkurthy, dives deep into the challenges faced when dealing with Head CT scans and medical imaging, and what creative ways can be used to address these challenges. As reported in this blog post, the main challenge seems to be in the processing and preparation of the medical images as it requires different processing techniques compared to the more common computer vision or natural language datasets and tasks.

→ Deep learning models were used to detect critical findings in head CT scans.

→ Google has developed an algorithm to detect the spread of breast cancer.

→ Amazon has released comprehend a machine-learning services for PHI and medical entities along with BlazingText for clinical Text Classification

→ We have seen the success of integrating different NLP techniques in designing conversational agents and recommendation systems, however, one of the promising areas where NLP will be heavily used in the future is in clinical informatics research. This review paper looks at the different NLP methods used in clinical research and the challenges involved in evaluating them.

→ James Zou et al. (2018) released a tutorial and guide on how to apply deep learning for genomics via a Google Colab notebook.

→ NLP researchers from National Tsing Hua University proposed a novel method for bipolar disorder prediction on social media based on an approach that leverages time-based features.

→ A syllabus on clinical linguistics.

→ BioBERT: pre-trained biomedical language representation model for biomedical text mining

→ Learn about how NLP can be used to leverage and unlock the unstructured healthcare datasets.

→ A recent study conducted by Dr. Fei Fei Li and team proposes a machine learning model that tracks your face and voice features and is able to predict the severity of depression.

→ Google AI announces improvements to their deep learning models used for diabetic retinopathy, one of the fastest growing causes of vision loss. The improvements include efforts to improve explainability and applicability in clinical settings.

→ Google AI opens new object detection competition which includes a massive training dataset.

→ Exciting paper on applying word embeddings to a massive source of multimodal medical data.

→ This exciting research focuses on using deep learning methods to detect linguistic cues of Alzheimer’s disease patients.

→ An impressive study on how to collect high-quality data through search queries in developing nations, which may have some serious health benefits for society.

→ Detecting social network mental disorders, such as internet overload and net compulsion, through a tensor decomposition approach.