A text-mining approach to obtain detailed treatment information from free-text fields in population-based cancer registries: A study of non-small cell lung cancer in California.

BACKGROUND: Population-based cancer registries have treatment information for all patients making them an excellent resource for population-level monitoring. However, specific treatment details, such as drug names, are contained in a free-text format that is difficult to process and summarize. We assessed the accuracy and efficiency of a text-mining algorithm to identify systemic treatments for lung cancer from free-text fields in the California Cancer Registry. METHODS: The algorithm used Perl regular expressions in SAS 9.4 to search for treatments in 24,845 free-text records associated with 17,310 patients in California diagnosed with stage IV non-small cell lung cancer between 2012 and 2014. Our algorithm categorized treatments into six groups that align with National Comprehensive Cancer Network guidelines. We compared results to a manual review (gold standard) of the same records. RESULTS: Percent agreement ranged from 91.1% to 99.4%. Ranges for other measures were 0.71-0.92 (Kappa), 74.3%-97.3% (sensitivity), 92.4%-99.8% (specificity), 60.4%-96.4% (positive predictive value), and 92.9%-99.9% (negative predictive value). The text-mining algorithm used one-sixth of the time required for manual review. CONCLUSION: SAS-based text mining of free-text data can accurately detect systemic treatments administered to patients and save considerable time compared to manual review, maximizing the utility of the extant information in population-based cancer registries for comparative effectiveness research.

In silico identification of anti-cancer compounds and plants from traditional Chinese medicine database.

There is a constant demand to develop new, effective, and affordable anti-cancer drugs. The traditional Chinese medicine (TCM) is a valuable and alternative resource for identifying novel anti-cancer agents. In this study, we aim to identify the anti-cancer compounds and plants from the TCM database by using cheminformatics. We first predicted 5278 anti-cancer compounds from TCM database. The top 346 compounds were highly potent active in the 60 cell lines test. Similarity analysis revealed that 75% of the 5278 compounds are highly similar to the approved anti-cancer drugs. Based on the predicted anti-cancer compounds, we identified 57 anti-cancer plants by activity enrichment. The identified plants are widely distributed in 46 genera and 28 families, which broadens the scope of the anti-cancer drug screening. Finally, we constructed a network of predicted anti-cancer plants and approved drugs based on the above results. The network highlighted the supportive role of the predicted plant in the development of anti-cancer drug and suggested different molecular anti-cancer mechanisms of the plants. Our study suggests that the predicted compounds and plants from TCM database offer an attractive starting point and a broader scope to mine for potential anti-cancer agents.

FINDING POTENTIALLY UNSAFE NUTRITIONAL SUPPLEMENTS FROM USER REVIEWS WITH TOPIC MODELING.

Although dietary supplements are widely used and generally are considered safe, some supplements have been identified as causative agents for adverse reactions, some of which may even be fatal. The Food and Drug Administration (FDA) is responsible for monitoring supplements and ensuring that supplements are safe. However, current surveillance protocols are not always effective. Leveraging user-generated textual data, in the form of Amazon.com reviews for nutritional supplements, we use natural language processing techniques to develop a system for the monitoring of dietary supplements. We use topic modeling techniques, specifically a variation of Latent Dirichlet Allocation (LDA), and background knowledge in the form of an adverse reaction dictionary to score products based on their potential danger to the public. Our approach generates topics that semantically capture adverse reactions from a document set consisting of reviews posted by users of specific products, and based on these topics, we propose a scoring mechanism to categorize products as "high potential danger", "average potential danger" and "low potential danger." We evaluate our system by comparing the system categorization with human annotators, and we find that the our system agrees with the annotators 69.4% of the time. With these results, we demonstrate that our methods show promise and that our system represents a proof of concept as a viable low-cost, active approach for dietary supplement monitoring.

Mining Novel Allergens from Coconut Pollen Employing Manual De Novo Sequencing and Homology-Driven Proteomics.

Coconut pollen, one of the major palm pollen grains is an important constituent among vectors of inhalant allergens in India and a major sensitizer for respiratory allergy in susceptible patients. To gain insight into its allergenic components, pollen proteins were analyzed by two-dimensional electrophoresis, immunoblotted with coconut pollen sensitive patient sera, followed by mass spectrometry of IgE reactive proteins. Coconut being largely unsequenced, a proteomic workflow has been devised that combines the conventional database-dependent analysis of tandem mass spectral data and manual de novo sequencing followed by a homology-based search for identifying the allergenic proteins. N-terminal acetylation helped to distinguish "b" ions from others, facilitating reliable sequencing. This led to the identification of 12 allergenic proteins. Cluster analysis with individual patient sera recognized vicilin-like protein as a major allergen, which was purified to assess its in vitro allergenicity and then partially sequenced. Other IgE-sensitive spots showed significant homology with well-known allergenic proteins such as 11S globulin, enolase, and isoflavone reductase along with a few which are reported as novel allergens. The allergens identified can be used as potential candidates to develop hypoallergenic vaccines, to design specific immunotherapy trials, and to enrich the repertoire of existing IgE reactive proteins.

Computational and experimental advances in drug repositioning for accelerated therapeutic stratification.

Drug repositioning is an important component of therapeutic stratification in the precision medicine paradigm. Molecular profiling and more sophisticated analysis of longitudinal clinical data are refining definitions of human diseases, creating needs and opportunities to re-target or reposition approved drugs for alternative indications. Drug repositioning studies have demonstrated success in complex diseases requiring improved therapeutic interventions as well as orphan diseases without any known treatments. An increasing collection of available computational and experimental methods that leverage molecular and clinical data enable diverse drug repositioning strategies. Integration of translational bioinformatics resources, statistical methods, chemoinformatics tools and experimental techniques (including medicinal chemistry techniques) can enable the rapid application of drug repositioning on an increasingly broad scale. Efficient tools are now available for systematic drug-repositioning methods using large repositories of compounds with biological activities. Medicinal chemists along with other translational researchers can play a key role in various aspects of drug repositioning. In this review article, we briefly summarize the history of drug repositioning, explain concepts behind drug repositioning methods, discuss recent computational and experimental advances and highlight available open access resources for effective drug repositioning investigations. We also discuss recent approaches in utilizing electronic health record for outcome assessment of drug repositioning and future avenues of drug repositioning in the light of targeting disease comorbidities, underserved patient communities, individualized medicine and socioeconomic impact.

Evaluating a federated medical search engine: tailoring the methodology and reporting the evaluation outcomes.

BACKGROUND: Federated medical search engines are health information systems that provide a single access point to different types of information. Their efficiency as clinical decision support tools has been demonstrated through numerous evaluations. Despite their rigor, very few of these studies report holistic evaluations of medical search engines and even fewer base their evaluations on existing evaluation frameworks. OBJECTIVES: To evaluate a federated medical search engine, MedSocket, for its potential net benefits in an established clinical setting. METHODS: This study applied the Human, Organization, and Technology (HOT-fit) evaluation framework in order to evaluate MedSocket. The hierarchical structure of the HOT-factors allowed for identification of a combination of efficiency metrics. Human fit was evaluated through user satisfaction and patterns of system use; technology fit was evaluated through the measurements of time-on-task and the accuracy of the found answers; and organization fit was evaluated from the perspective of system fit to the existing organizational structure. RESULTS: Evaluations produced mixed results and suggested several opportunities for system improvement. On average, participants were satisfied with MedSocket searches and confident in the accuracy of retrieved answers. However, MedSocket did not meet participants' expectations in terms of download speed, access to information, and relevance of the search results. These mixed results made it necessary to conclude that in the case of MedSocket, technology fit had a significant influence on the human and organization fit. Hence, improving technological capabilities of the system is critical before its net benefits can become noticeable. CONCLUSIONS: The HOT-fit evaluation framework was instrumental in tailoring the methodology for conducting a comprehensive evaluation of the search engine. Such multidimensional evaluation of the search engine resulted in recommendations for system improvement.

[Construction and thinking of data element standard directory of traditional Chinese medicine clinical pharmacy information].

The aim of this study was to develop the data element standard directory of traditional Chinese medicine (TCM) clinical pharmacy information, to provide application standards and models of TCM clinical pharmacy for the electronic medical record (EMR). The developed line of work is as follows: initially establish research through four forms: literature analysis, questionnaires, discussion groups, expert advice. The research range from the Chinese herbal medicine research, herbal origin, harvesting, processing, identification of traits, physical and chemical identification, modern research, character, taste, Indications, clinical application, processing, dispensing medicine, Chinese medicine specifications, usage, dosage, caution, efficacy indications to small packaging applications, drug research, management and other related issues, including traditional Chinese medicine theory, application and hospital management information; according to the general and part 16 content of the national "Health Information Data Element Standards", and the basic method of extracting data element to study and develop the data element of TCM clinical pharmacy information from the defining content. Correspondingly propose the ideas and methods of construction of the "Data Element Standard Directory of TCM Clinical Pharmacy Information", sort out medicine clinical information data element standard catalog, divided into basic categories, clinical application class, management class three parts, and set norms and standards of identifying data elements, definitions, allowable value of traditional Chinese medicine clinical information, and discuss the sources and standards of information collection, leaving the interface, standardized and scientific terminology, docking with the existing standards, maintenance and management program and oter issues.

Association rule mining and network analysis in oriental medicine.

Extracting useful and meaningful patterns from large volumes of text data is of growing importance. In the present study we analyze vast amounts of prescription data, generated from the book of oriental medicine to identify the relationships between the symptoms and the associated medicines used to treat these symptoms. The oriental medicine book used in this study (called Bangyakhappyeon) contains a large number of prescriptions to treat about 54 categorized symptoms and lists the corresponding herbal materials. We used an association rule algorithm combined with network analysis and found useful and informative relationships between the symptoms and medicines.

Component analysis of Chinese medicine and advances in fuming-washing therapy for knee osteoarthritis via unsupervised data mining methods.

OBJECTIVE: To analyze the component law of Chinese medicines in fuming-washing therapy for knee osteoarthritis (KOA), and develop new fuming-washing prescriptions for KOA through unsupervised data mining methods. METHODS: Chinese medicine recipes for fuming-washing therapy for KOA were collected and recorded in a database. The correlation coefficient among herbs, core combinations of herbs, and new prescriptions were analyzed using modified mutual information, complex system entropy cluster, and unsupervised hierarchical clustering, respectively. RESULTS: Based on analysis of 345 Chinese medicine recipes for fuming-washing therapy, 68 herbs occurred frequently, 33 herb pairs occurred frequently, and 12 core combinations were found. Five new fuming-washing recipes for KOA were developed. CONCLUSION: Chinese medicines for fuming-washing therapy of KOA mainly consist of wind-dampness-dispelling and cold-dispersing herbs, blood-activating and stasis-resolving herbs, and wind-dampness-dispelling and heat-clearing herbs. The treatment of fuming-washing therapy for KOA also includes dispelling wind-dampness and dispersing cold, activating blood and resolving stasis, and dispelling wind-dampness and clearing heat. Zhenzhutougucao (Herba Speranskiae Tuberculatae), Honghua (Flos Carthami), Niuxi (Radix Achyranthis Bidentatae), Shenjincao (Herba Lycopodii Japonici), Weilingxian (Radix et Rhizoma Clematidis Chinensis), Chuanwu (Radix Aconiti), Haitongpi (Cortex Erythrinae Variegatae), Ruxiang (Olibanum), Danggui (Radix Angelicae Sinensis), Caowu (Radix Aconiti Kusnezoffii), Moyao (Myrrha), and Aiye (Folium Artemisiae Argyi) are the main herbs used in the fuming-washing treatment for KOA.

Heart rate variability: an index of brain processing in vegetative state? An artificial intelligence, data mining study.

OBJECTIVE: Brain processing at varying levels of functional complexity has been documented in vegetative state. In this study, data mining procedures are applied to identify significant changes in heart rate variability (an emerging objective descriptor of autonomic correlates of brain activation) in response to complex auditory stimuli with emotional value (music). METHODS: The heart rate of subjects in vegetative state from brain damage (n=6) or spontaneous hemorrhage (n=3) and 16 healthy controls was recorded while they passively listened to four pre-selected music samples by different authors (mean recording time: 3m and 36s±24s). The parametric and non-parametric frequency spectra were computed on the heart rate, spectra were compared within/across subjects and music authors, and the spectra descriptors were entered into a 1-R rules data mining procedure (WEKA software Leave One Out and Ten Fold Cross validation). The procedure independently classified the heart rate spectral patterns of both patients and controls and the emotions reported by healthy subjects as "positive" or "negative". RESULTS: In both healthy controls and vegetative state subjects, the power spectra while passively listening to music differed from baseline when compared irrespective of the music authorship and from each other when compared across music samples. Data mining sorted the nu_LF (normalized parameter unit of the spectrum low frequency range) as the significant descriptor of heart rate variability in the conditions of the study. The nu_LF classification of the healthy controls' HRV changes in response to music replicated that based on subjective reports with 75-93.7% accuracy. CONCLUSIONS: Although preliminary, these findings suggest that autonomic changes with possible emotional value can be induced by complex stimuli also in vegetative state, with implications on the residual responsiveness of these subjects. SIGNIFICANCE: Heart rate variability descriptors and data mining methods appear applicable to investigate brain function in the absence of consciousness.