Charles Yee

The problem of clinical trial matching is to extract the relevant eligibility criteria from more than 40,000 clinical trial protocols and then match them to the given cancer patient's profile. The relevant matching criteria include cancer type, staging, genetic mutations, the patient's demographics, and comorbidities. This is an extremely complex NLP problem applied across big data.

With my team, I evolved a naive, Elasticsearch approach to a pipeline using a hybrid of named entity recognition (NER) and logical satisfiability theory. We successfully trained a long short-term memory neural network (LSTM) with a conditional random field (CRF) output layer using clinical domain-informed corpora as word embedding.

As a result of our work, my team successfully achieved more than 95% accuracy in automated clinical trial matching—as validated by pathologists and oncologists.

The project yielded impressive results that saved tremendous time for clinicians. It is now a commercial success, replacing IBM Watson and deployed as part of the Philips Intellispace Genomics solution at the nation's top cancer institutions such as Dana-Farber, MD Anderson, and Boston Children's hospital.

Charles led a team of seven to build a three-layered hybrid NLP ICD10 extraction microservice infrastructure. First, all pdf scans of EHR are OCR'ed into text using Tesseract. The content of EHR's is stored in JSON format in a MongoDB. These texts then go through a rule-based, hashmap-like system where every clinical term, acronyms, synonyms are converted to their subsequent ICD10 code. However, this alone has a high false-positive rate, albeit an extremely high recall (>98%). A layer of Transformer network using ClincalBERT and BioBERT is then applied on top of the rule-based output to perform binary classification, eliminating false positives to provide highly accurate ICD10 that is context-sensitive and clinically relevant.

Various embodiments relate to a method and non-transitory computer-readable medium for genome spelling correction.

The method included the steps of performing pre-processing on a sentence:
1. Storing a first adjacent word to an unknown word and a second adjacent word to the unknown word
2. Generating a plurality of candidate words for the unknown word
3. Forming a plurality of trigrams with the first adjacent word to the unknown word and the second adjacent word to the unknown word and each of the plurality of candidate words
4. Searching a trigram table for each of the plurality of trigrams
5. Outputting the candidate word from the trigram with the highest trigram count in the trigram table