ABSTRACT
Differential diagnosis is a crucial aspect of medical practice, as it guides clinicians to accurate diagnoses and effective treatment plans. Traditional resources, such as medical books and services like UpToDate, are constrained by manual curation, potentially missing out on novel or less common findings. This paper introduces and analyzes two novel methods to mine etiologies from scientific literature. The first method employs a traditional Natural Language Processing (NLP) approach based on syntactic patterns. By using a novel application of human-guided pattern bootstrapping patterns are derived quickly, and symptom etiologies are extracted with significant coverage. The second method utilizes generative models, specifically GPT-4, coupled with a fact verification pipeline, marking a pioneering application of generative techniques in etiology extraction. Analyzing this second method shows that while it is highly precise, it offers lesser coverage compared to the syntactic approach. Importantly, combining both methodologies yields synergistic outcomes, enhancing the depth and reliability of etiology mining.
Subject(s)
Natural Language Processing , Humans , Data Mining/methods , Diagnosis, Differential , AlgorithmsABSTRACT
Drug combination therapy is a main pillar of cancer therapy. As the number of possible drug candidates for combinations grows, the development of optimal high complexity combination therapies (involving 4 or more drugs per treatment) such as RCHOP-I and FOLFIRINOX becomes increasingly challenging due to combinatorial explosion. In this paper, we propose a text mining (TM) based tool and workflow for rapid generation of high complexity combination treatments (HCCT) in order to extend the boundaries of complexity in cancer treatments. Our primary objectives were: (1) Characterize the existing limitations in combination therapy; (2) Develop and introduce the Plan Builder (PB) to utilize existing literature for drug combination effectively; (3) Evaluate PB's potential in accelerating the development of HCCT plans. Our results demonstrate that researchers and experts using PB are able to create HCCT plans at much greater speed and quality compared to conventional methods. By releasing PB, we hope to enable more researchers to engage with HCCT planning and demonstrate its clinical efficacy.
Subject(s)
Antineoplastic Combined Chemotherapy Protocols , Pancreatic Neoplasms , Humans , Drug Combinations , Data Mining/methodsABSTRACT
OBJECTIVE: To demonstrate and develop an approach enabling individual researchers or small teams to create their own ad-hoc, lightweight knowledge bases tailored for specialized scientific interests, using text-mining over scientific literature, and demonstrate the effectiveness of these knowledge bases in hypothesis generation and literature-based discovery (LBD). METHODS: We propose a lightweight process using an extractive search framework to create ad-hoc knowledge bases, which require minimal training and no background in bio-curation or computer science. These knowledge bases are particularly effective for LBD and hypothesis generation using Swanson's ABC method. The personalized nature of the knowledge bases allows for a somewhat higher level of noise than "public facing" ones, as researchers are expected to have prior domain experience to separate signal from noise. Fact verification is shifted from exhaustive verification of the knowledge base to post-hoc verification of specific entries of interest, allowing researchers to assess the correctness of relevant knowledge base entries by considering the paragraphs in which the facts were introduced. RESULTS: We demonstrate the methodology by constructing several knowledge bases of different kinds: three knowledge bases that support lab-internal hypothesis generation: Drug Delivery to Ovarian Tumors (DDOT); Tissue Engineering and Regeneration; Challenges in Cancer Research; and an additional comprehensive, accurate knowledge base designated as a public resource for the wider community on the topic of Cell Specific Drug Delivery (CSDD). In each case, we show the design and construction process, along with relevant visualizations for data exploration, and hypothesis generation. For CSDD and DDOT we also show meta-analysis, human evaluation, and in vitro experimental evaluation. CONCLUSION: Our approach enables researchers to create personalized, lightweight knowledge bases for specialized scientific interests, effectively facilitating hypothesis generation and literature-based discovery (LBD). By shifting fact verification efforts to post-hoc verification of specific entries, researchers can focus on exploring and generating hypotheses based on their expertise. The constructed knowledge bases demonstrate the versatility and adaptability of our approach to versatile research interests. The web-based platform, available at https://spike-kbc.apps.allenai.org, provides researchers with a valuable tool for rapid construction of knowledge bases tailored to their needs.