Application of artificial intelligence to overcome clinical information overload in urological cancer.

OBJECTIVE: To describe the use of artificial intelligence (AI) in medical literature and trial data extraction, and its applications in uro-oncology. This bridging review, which consolidates information from the diverse applications of AI, highlights how AI users can investigate more sophisticated queries than with traditional methods, leading to synthesis of raw data and complex outputs into more actionable and personalised results, particularly in the field of uro-oncology. METHODS: Literature and clinical trial searches were performed in PubMed, Dimensions, Embase and Google (1999-2020). The searches focussed on the use of AI and its various forms to facilitate literature searches, clinical guidelines development, and clinical trial data extraction in uro-oncology. To illustrate how AI can be applied to address questions about optimising therapeutic decision making and individualising treatment regimens, the Dimensions-linked information platform was searched for 'prostate cancer' keywords (76 publications were identified; 48 were included). RESULTS: AI offers the promise of transforming raw data and complex outputs into actionable insights. Literature and clinical trial searches can be automated, enabling clinicians to develop and analyse publications expeditiously on complex issues such as therapeutic sequencing and to obtain updates on documents that evolve at the pace and scope of the landscape. An AI-based platform inclusive of 12 trial databases and >100 scientific literature sources enabled the creation of an interactive visualisation. CONCLUSION: As the literature and clinical trial landscape continues to grow in complexity and with increasing speed, the ability to pull the right information at the right time from different search engines and resources, while excluding social media bias, becomes more challenging. This review demonstrates that by applying natural language processing and machine learning algorithms, validated and optimised AI leads to a speedier, more personalised, efficient, and focussed search compared with traditional methods.

Artificial INtelligence to Support Informed DEcision-making (INSIDE) for Improved Literature Analysis in Oncology.

BACKGROUND: Defining optimal therapeutic sequencing strategies in prostate cancer (PC) is challenging and may be assisted by artificial intelligence (AI)-based tools for an analysis of the medical literature. OBJECTIVE: To demonstrate that INSIDE PC can help clinicians query the literature on therapeutic sequencing in PC and to develop previously unestablished practices for evaluating the outputs of AI-based support platforms. DESIGN, SETTING, AND PARTICIPANTS: INSIDE PC was developed by customizing PubMed Bidirectional Encoder Representations from Transformers. Publications were ranked and aggregated for relevance using data visualization and analytics. Publications returned by INSIDE PC and PubMed were given normalized discounted cumulative gain (nDCG) scores by PC experts reflecting ranking and relevance. INTERVENTION: INSIDE PC for AI-based semantic literature analysis. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: INSIDE PC was evaluated for relevance and accuracy for three test questions on the efficacy of therapeutic sequencing of systemic therapies in PC. RESULTS AND LIMITATIONS: In this initial evaluation, INSIDE PC outperformed PubMed for question 1 (novel hormonal therapy [NHT] followed by NHT) for the top five, ten, and 20 publications (nDCG score, +43, +33, and +30 percentage points [pps], respectively). For question 2 (NHT followed by poly [adenosine diphosphate ribose] polymerase inhibitors [PARPi]), INSIDE PC and PubMed performed similarly. For question 3 (NHT or PARPi followed by 177Lu-prostate-specific membrane antigen-617), INSIDE PC outperformed PubMed for the top five, ten, and 20 publications (+16, +4, and +5 pps, respectively). CONCLUSIONS: We applied INSIDE PC to develop standards for evaluating the performance of AI-based tools for literature extraction. INSIDE PC performed competitively with PubMed and can assist clinicians with therapeutic sequencing in PC. PATIENT SUMMARY: The medical literature is often very difficult for doctors and patients to search. In this report, we describe INSIDE PC-an artificial intelligence (AI) system created to help search articles published in medical journals and determine the best order of treatments for advanced prostate cancer in a much better time frame. We found that INSIDE PC works as well as another search tool, PubMed, a widely used resource for searching and retrieving articles published in medical journals. Our work with INSIDE PC shows new ways in which AI can be used to search published articles in medical journals and how these systems might be evaluated to support shared decision-making.

A dictionary to identify small molecules and drugs in free text.

MOTIVATION: From the scientific community, a lot of effort has been spent on the correct identification of gene and protein names in text, while less effort has been spent on the correct identification of chemical names. Dictionary-based term identification has the power to recognize the diverse representation of chemical information in the literature and map the chemicals to their database identifiers. RESULTS: We developed a dictionary for the identification of small molecules and drugs in text, combining information from UMLS, MeSH, ChEBI, DrugBank, KEGG, HMDB and ChemIDplus. Rule-based term filtering, manual check of highly frequent terms and disambiguation rules were applied. We tested the combined dictionary and the dictionaries derived from the individual resources on an annotated corpus, and conclude the following: (i) each of the different processing steps increase precision with a minor loss of recall; (ii) the overall performance of the combined dictionary is acceptable (precision 0.67, recall 0.40 (0.80 for trivial names); (iii) the combined dictionary performed better than the dictionary in the chemical recognizer OSCAR3; (iv) the performance of a dictionary based on ChemIDplus alone is comparable to the performance of the combined dictionary. AVAILABILITY: The combined dictionary is freely available as an XML file in Simple Knowledge Organization System format on the web site http://www.biosemantics.org/chemlist.

Intraindividual variability in electrocardiograms.

The electrocardiogram (ECG) can be affected by intraindividual variations from various sources that may confuse the diagnosis of the underlying cardiac condition and impair the accuracy of ECG interpretation. Intraindividual variability is a hindrance in serial ECG analysis, where ECGs of the same individual, but taken at different times, are compared. Two sources of intraindividual variability can be distinguished as follows: variability related to the technical circumstances during ECG recording (technical sources) and nonpathologic biologic variability (biological sources). Among the technical sources, variation in electrode positioning between recordings is the most confusing. Of the biological sources, respiratory variations are effective at any time scale, but the most important are age and weight that work on prolonged time scales. Technical problems are best prevented by rigorously sticking to a standard acquisition protocol. Criteria can be adapted to changing circumstances (age, weight), and by computer modeling, it may be possible to correct the ECG diagnosis for some sources of intraindividual variability.

Thesaurus-based disambiguation of gene symbols.

BACKGROUND: Massive text mining of the biological literature holds great promise of relating disparate information and discovering new knowledge. However, disambiguation of gene symbols is a major bottleneck. RESULTS: We developed a simple thesaurus-based disambiguation algorithm that can operate with very little training data. The thesaurus comprises the information from five human genetic databases and MeSH. The extent of the homonym problem for human gene symbols is shown to be substantial (33% of the genes in our combined thesaurus had one or more ambiguous symbols), not only because one symbol can refer to multiple genes, but also because a gene symbol can have many non-gene meanings. A test set of 52,529 Medline abstracts, containing 690 ambiguous human gene symbols taken from OMIM, was automatically generated. Overall accuracy of the disambiguation algorithm was up to 92.7% on the test set. CONCLUSION: The ambiguity of human gene symbols is substantial, not only because one symbol may denote multiple genes but particularly because many symbols have other, non-gene meanings. The proposed disambiguation approach resolves most ambiguities in our test set with high accuracy, including the important gene/not a gene decisions. The algorithm is fast and scalable, enabling gene-symbol disambiguation in massive text mining applications.

Research for research: tools for knowledge discovery and visualization.

This paper describes a method to construct from a set of documents a spatial representation that can be used for information retrieval and knowledge discovery. The proposed method has been implemented in a prototype system and allows the researcher to browse interactively and in real-time a network of relationships obtained from a set of full text articles. These relationships are combined with the potential relationships between concepts as defined in the UMLS semantic network. The browser allows the user to select a seed term and find all related concepts, to find a path between concepts (hypothesis testing), and to retrieve the references to documents or database entries that support the relationship between concepts.