-
BMC Medical Informatics and Decision... Jul 2023Real-world evidence (RWE)-based on information obtained from sources such as electronic health records (EHRs), claims and billing databases, product and disease...
BACKGROUND
Real-world evidence (RWE)-based on information obtained from sources such as electronic health records (EHRs), claims and billing databases, product and disease registries, and personal devices and health applications-is increasingly used to support healthcare decision making. There is variability in the collection of EHR data, which includes "structured data" in predefined fields (e.g., problem list, open claims, medication list, etc.) and "unstructured data" as free text or narrative. Healthcare providers are likely to provide more complete information as free text, but extracting meaning from these fields requires newer technologies and a rigorous methodology to generate higher-quality evidence. Herein, an approach to identify concepts associated with the presence and progression of migraine was developed and validated using the complete patient record in EHR data, including both the structured and unstructured portions.
METHODS
"Traditional RWE" approaches (i.e., capture from structured EHR fields and extraction using structured queries) and "Advanced RWE" approaches (i.e., capture from unstructured EHR data and processing by artificial intelligence [AI] technology, including natural language processing and AI-based inference) were evaluated against a manual chart abstraction reference standard for data collected from a tertiary care setting. The primary endpoint was recall; differences were compared using chi square.
RESULTS
Compared with manual chart abstraction, recall for migraine and headache were 66.6% and 29.6%, respectively, for Traditional RWE, and 96.8% and 92.9% for Advanced RWE; differences were statistically significant (absolute differences, 30.2% and 63.3%; P < 0.001). Recall of 6 migraine-associated symptoms favored Advanced RWE over Traditional RWE to a greater extent (absolute differences, 71.5-88.8%; P < 0.001). The difference between traditional and advanced techniques for recall of migraine medications was less pronounced, approximately 80% for Traditional RWE and ≥ 98% for Advanced RWE (P < 0.001).
CONCLUSION
Unstructured EHR data, processed using AI technologies, provides a more credible approach to enable RWE in migraine than using structured EHR and claims data alone. An algorithm was developed that could be used to further study and validate the use of RWE to support diagnosis and management of patients with migraine.
Topics: Humans; Electronic Health Records; Artificial Intelligence; Algorithms; Natural Language Processing; Migraine Disorders
PubMed: 37452338
DOI: 10.1186/s12911-023-02190-8 -
Sensors (Basel, Switzerland) Jan 2024Transactional data from point-of-sales systems may not consider customer behavior before purchasing decisions are finalized. A smart shelf system would be able to...
Transactional data from point-of-sales systems may not consider customer behavior before purchasing decisions are finalized. A smart shelf system would be able to provide additional data for retail analytics. In previous works, the conventional approach has involved customers standing directly in front of products on a shelf. Data from instances where customers deviated from this convention, referred to as "cross-location", were typically omitted. However, recognizing instances of cross-location is crucial when contextualizing multi-person and multi-product tracking for real-world scenarios. The monitoring of product association with customer keypoints through RANSAC modeling and particle filtering (PACK-RMPF) is a system that addresses cross-location, consisting of twelve load cell pairs for product tracking and a single camera for customer tracking. In this study, the time series vision data underwent further processing with R-CNN and StrongSORT. An NTP server enabled the synchronization of timestamps between the weight and vision subsystems. Multiple particle filtering predicted the trajectory of each customer's centroid and wrist keypoints relative to the location of each product. RANSAC modeling was implemented on the particles to associate a customer with each event. Comparing system-generated customer-product interaction history with the shopping lists given to each participant, the system had a general average recall rate of 76.33% and 79% for cross-location instances over five runs.
Topics: Humans; Supermarkets; Commerce; Research Personnel; Sprains and Strains; Standing Position
PubMed: 38257460
DOI: 10.3390/s24020367 -
Drug Discovery Today Jun 2024To introduce products in the US market, pharmaceutical companies must first obtain FDA clearance. Manufacturers might recall a product if it poses a risk of damage or... (Review)
Review
To introduce products in the US market, pharmaceutical companies must first obtain FDA clearance. Manufacturers might recall a product if it poses a risk of damage or violates FDA regulations. This study investigates the types, causes and consequences of recalls, as well as FDA participation and suitable recall strategies. We relied on the FDA website to gather recall data sets from 2012 to 2023, collecting information on the date of issuance, company and type of violation. The most frequent causes for recalls were sterility issues and inadequate compliance with current good manufacturing practices (cGMP). An examination of sterility recalls revealed two primary causes: a lack of assurance in sterility (accounting for 48% of recalls) and instances of non-sterility (making up 45% of recalls). A thorough examination of cGMP recalls revealed five primary types of violations: process control issues, inadequate storage practices, manufacturing problems, the presence of nitroso-amine impurities and concerns regarding stability. The findings demonstrate that sterility and cGMP compliance are FDA priorities. Pharmaceutical companies must, therefore, enhance quality compliance and create effective quality management systems that oversee the manufacturing process, quality control, personnel training and documentation to avoid these recalls. Companies should establish an internal compliance checklist and be prepared for the rectification process.
Topics: United States; United States Food and Drug Administration; Drug Industry; Drug Recalls; Humans; Retrospective Studies
PubMed: 38670257
DOI: 10.1016/j.drudis.2024.103993 -
HIV/AIDS (Auckland, N.Z.) 2023Poor adherence to antiretroviral therapy (ART) causes drug resistance, treatment failure and death. Studies conducted among children below 15 years were limited in...
BACKGROUND
Poor adherence to antiretroviral therapy (ART) causes drug resistance, treatment failure and death. Studies conducted among children below 15 years were limited in Ethiopia in general and in the study area. Therefore, this study aimed to assess the status of children's adherence to ART and associated factors in the study area.
METHODS
We conducted a facility-based cross-sectional study from April 1 to May 10, 2020 by including 282 children <15 years. All children who received ART for at least one month and attend ART clinic during data collection period were consecutively recruited. Face-to-face interview was conducted using a standardized questionnaire. Both bivariate and multivariate logistic regression were performed. Adherence and exposure variables (i.e., sociodemographic and reason for missing) were measured by the caregivers/children's report of a one-month recall of missed doses.
RESULTS
Among 282 caregivers included with their children, 226 (80.2%) were females (mean age = 38.6 and SD = 12.35) and half (50%) of children were females. Two hundred forty six (87.2%) children were aged between 5-14 years (mean age = 8.5 and SD = 2.64), and 87.2% were adhered (≥95%) to ART in the month prior to the interview. Children whose caregivers were residing in urban were 3.3 (95% CI: 1.17, 9.63) times more adherent to ART than their counterparties. Children whose caregivers were biological parents were 2.37 (95% CI: 1.59, 3.3) times more adherent than children with non-biological parents. Children with knowledgeable caregivers about ART were 4.5 (95% CI: 1.79, 9.8) times more adherent to ART.
CONCLUSION AND RECOMMENDATION
Children's adherence to ART in our study area was sub optimal. Biological caregivers, residing in urban and being knowledgeable about ART facilitate adherence to ART. Adherence counseling targeting non-biological parents and for those who come from rural areas were recommended.
PubMed: 37497118
DOI: 10.2147/HIV.S407105 -
BioRxiv : the Preprint Server For... Jun 2023Sleep supports memory consolidation. However, it is not completely clear how different sleep stages contribute to this process. While rapid eye movement sleep (REM) has...
Sleep supports memory consolidation. However, it is not completely clear how different sleep stages contribute to this process. While rapid eye movement sleep (REM) has traditionally been implicated in the processing of emotionally charged material, recent studies indicate a role for slow wave sleep (SWS) in strengthening emotional memories. Here, to directly examine which sleep stage is primarily involved in emotional memory consolidation, we used targeted memory reactivation (TMR) in REM and SWS during a daytime nap. Contrary to our hypothesis, reactivation of emotional stimuli during REM led to impaired memory. Consistent with this, REM% was correlated with worse recall in the group that took a nap without TMR. Meanwhile, cueing benefit in SWS was strongly correlated with the product of times spent in REM and SWS (SWS-REM product), and reactivation significantly enhanced memory in those with high SWS-REM product. Surprisingly, SWS-REM product was associated with better memory for reactivated items and poorer memory for non-reactivated items, suggesting that sleep both preserved and eliminated emotional memories, depending on whether they were reactivated. Notably, the emotional valence of cued items modulated both sleep spindles and delta/theta power. Finally, we found that emotional memories benefited from TMR more than did neutral ones. Our results suggest that emotional memories decay during REM, unless they are reactivated during prior SWS. Furthermore, we show that active forgetting complements memory consolidation, and both take place across SWS and REM. In addition, our findings expand upon recent evidence indicating a link between sleep spindles and emotional processing.
PubMed: 36909630
DOI: 10.1101/2023.03.01.530661 -
PeerJ. Computer Science 2024Opinion mining is gaining significant research interest, as it directly and indirectly provides a better avenue for understanding customers, their sentiments toward a...
Opinion mining is gaining significant research interest, as it directly and indirectly provides a better avenue for understanding customers, their sentiments toward a service or product, and their purchasing decisions. However, extracting every opinion feature from unstructured customer review documents is challenging, especially since these reviews are often written in native languages and contain grammatical and spelling errors. Moreover, existing pattern rules frequently exclude features and opinion words that are not strictly nouns or adjectives. Thus, selecting suitable features when analyzing customer reviews is the key to uncovering their actual expectations. This study aims to enhance the performance of explicit feature extraction from product review documents. To achieve this, an approach that employs sequential pattern rules is proposed to identify and extract features with associated opinions. The improved pattern rules total 41, including 16 new rules introduced in this study and 25 existing pattern rules from previous research. An average calculated from the testing results of five datasets showed that the incorporation of this study's 16 new rules significantly improved feature extraction precision by 6%, recall by 6% and F-measure value by 5% compared to the contemporary approach. The new set of rules has proven to be effective in extracting features that were previously overlooked, thus achieving its objective of addressing gaps in existing rules. Therefore, this study has successfully enhanced feature extraction results, yielding an average precision of 0.91, an average recall value of 0.88, and an average F-measure of 0.89.
PubMed: 38435547
DOI: 10.7717/peerj-cs.1821 -
Proceedings. IEEE International... Dec 2023Tandem mass spectrometry (MS/MS) stands as the predominant high-throughput technique for comprehensively analyzing protein content within biological samples. This...
Tandem mass spectrometry (MS/MS) stands as the predominant high-throughput technique for comprehensively analyzing protein content within biological samples. This methodology is a cornerstone driving the advancement of proteomics. In recent years, substantial strides have been made in Data-Independent Acquisition (DIA) strategies, facilitating impartial and non-targeted fragmentation of precursor ions. The DIA-generated MS/MS spectra present a formidable obstacle due to their inherent high multiplexing nature. Each spectrum encapsulates fragmented product ions originating from multiple precursor peptides. This intricacy poses a particularly acute challenge in de novo peptide/protein sequencing, where current methods are ill-equipped to address the multiplexing conundrum. In this paper, we introduce Casanovo-DIA, a deep-learning model based on transformer architecture. It deciphers peptide sequences from DIA mass spectrometry data. Our results show significant improvements over existing STOA methods, including DeepNovo-DIA and PepNet. Casanovo-DIA enhances precision by 15.14% to 34.8%, recall by 11.62% to 31.94% at the amino acid level, and boosts precision by 59% to 81.36% at the peptide level. Integrating DIA data and our Casanovo-DIA model holds considerable promise to uncover novel peptides and more comprehensive profiling of biological samples. Casanovo-DIA is freely available under the GNU GPL license at https://github.com/Biocomputing-Research-Group/Casanovo-DIA.
PubMed: 38665266
DOI: 10.1109/bibe60311.2023.00013 -
Research (Washington, D.C.) 2023Three-dimensional (3D) printing is emerging as a transformative technology for biomedical engineering. The 3D printed product can be patient-specific by allowing...
Three-dimensional (3D) printing is emerging as a transformative technology for biomedical engineering. The 3D printed product can be patient-specific by allowing customizability and direct control of the architecture. The trial-and-error approach currently used for developing the composition of printable inks is time- and resource-consuming due to the increasing number of variables requiring expert knowledge. Artificial intelligence has the potential to reshape the ink development process by forming a predictive model for printability from experimental data. In this paper, we constructed machine learning (ML) algorithms including decision tree, random forest (RF), and deep learning (DL) to predict the printability of biomaterials. A total of 210 formulations including 16 different bioactive and smart materials and 4 solvents were 3D printed, and their printability was assessed. All ML methods were able to learn and predict the printability of a variety of inks based on their biomaterial formulations. In particular, the RF algorithm has achieved the highest accuracy (88.1%), precision (90.6%), and F1 score (87.0%), indicating the best overall performance out of the 3 algorithms, while DL has the highest recall (87.3%). Furthermore, the ML algorithms have predicted the printability window of biomaterials to guide the ink development. The printability map generated with DL has finer granularity than other algorithms. ML has proven to be an effective and novel strategy for developing biomaterial formulations with desired 3D printability for biomedical engineering applications.
PubMed: 37469394
DOI: 10.34133/research.0197 -
Annals of Work Exposures and Health Feb 2024Cleaning product use has been associated with adverse respiratory health effects such as asthma in cleaning staff and healthcare workers. Research in health effects from...
BACKGROUND
Cleaning product use has been associated with adverse respiratory health effects such as asthma in cleaning staff and healthcare workers. Research in health effects from cleaning products has largely depended upon collecting exposure information by questionnaires which has limitations such as recall bias and underestimation of exposure. The aim of this study was to develop a Cleaning and Hazardous Products Exposure Logging (CHaPEL) app with a barcode scanner and to test the feasibility of this app with university cleaners.
METHODS
The CHaPEL app was developed to collect information on demographics, individual product information, and exposure information. It also included an ease-of-use survey. A pilot study with university cleaning workers was undertaken in which cleaning workers scanned each product after use and answered the survey. Respiratory hazards of cleaning substances in the scanned cleaning products were screened by safety data sheets, a Quantitative Structure-Activity Relationship model and an asthmagen list established by an expert group in the US.
RESULTS
Eighteen university cleaners participated in this study over a period of 5 weeks. In total, 77 survey responses and 6 cleaning products were collected and all reported that using the app was easy. The most frequently used product was a multi-surface cleaner followed by a disinfectant. Out of 14 substances in cleaning products, ethanolamine and Alkyl (C12-16) dimethyl benzyl ammonium chloride were found as respiratory hazardous substances.
CONCLUSION
The CHaPEL app is a user-friendly immediate way to successfully collect exposure information using the barcodes of cleaning products. This tool could be useful for future epidemiological studies focused on exposure assessment with less interruption to the workers.
Topics: Humans; Occupational Exposure; Pilot Projects; Mobile Applications; Hazardous Substances; Asthma
PubMed: 38142412
DOI: 10.1093/annweh/wxad082 -
Analytical and Bioanalytical Chemistry Jul 2023Bear bile powder (BBP) is a valuable animal-derived product with a huge adulteration problem on market. It is a crucially important task to identify BBP and its...
Bear bile powder (BBP) is a valuable animal-derived product with a huge adulteration problem on market. It is a crucially important task to identify BBP and its counterfeit. Electronic sensory technologies are the inheritance and development of traditional empirical identification. Considering that each drug has its own specific odor and taste characteristics, electronic tongue (E-tongue), electronic nose (E-nose) and GC-MS were used to evaluate the aroma and taste of BBP and its common counterfeit. Two active components of BBP, namely tauroursodeoxycholic acid (TUDCA) and taurochenodeoxycholic acid (TCDCA) were measured and linked with the electronic sensory data. The results showed that bitterness was the main flavor of TUDCA in BBP, saltiness and umami were the main flavor of TCDCA. The volatiles detected by E-nose and GC-MS were mainly aldehydes, ketones, alcohols, hydrocarbons, carboxylic acids, heterocyclic, lipids, and amines, mainly earthy, musty, coffee, bitter almond, burnt, pungent odor descriptions. Four different machine learning algorithms (backpropagation neural network, support vector machine, K-nearest neighbor, and random forest) were used to identify BBP and its counterfeit, and the regression performance of these four algorithms was also evaluated. For qualitative identification, the algorithm of random forest has shown the best performance, with 100% accuracy, precision, recall and F1-score. Also, the random forest algorithm has the best R and the lowest RMSE in terms of quantitative prediction.
Topics: Animals; Electronic Nose; Ursidae; Powders; Bile; Tongue
PubMed: 37199792
DOI: 10.1007/s00216-023-04740-5