RESUMO
Background: Cystic fibrosis (CF) is a genetic disease but is greatly impacted by non-genetic (social/environmental and stochastic) influences. Some people with CF experience rapid decline, a precipitous drop in lung function relative to patient- and/or center-level norms. Those who experience rapid decline in early adulthood, compared to adolescence, typically exhibit less severe clinical disease but greater loss of lung function. The extent to which timing and degree of rapid decline are informed by social and environmental determinants of health (geomarkers) is unknown. Methods: A longitudinal cohort study was performed (24,228 patients, aged 6-21 years) using the U.S. CF Foundation Patient Registry. Geomarkers at the ZIP Code Tabulation Area level measured air pollution/respiratory hazards, greenspace, crime, and socioeconomic deprivation. A composite score quantifying social-environmental adversity was created and used in covariate-adjusted functional principal component analysis, which was applied to cluster longitudinal lung function trajectories. Results: Social-environmental phenotyping yielded three primary phenotypes that corresponded to early, middle, and late timing of peak decline in lung function over age. Geographic differences were related to distinct cultural and socioeconomic regions. Extent of peak decline, estimated as forced expiratory volume in 1 s of % predicted/year, ranged from 2.8 to 4.1 % predicted/year depending on social-environmental adversity. Middle decliners with increased social-environmental adversity experienced rapid decline 14.2 months earlier than their counterparts with lower social-environmental adversity, while timing was similar within other phenotypes. Early and middle decliners experienced mortality peaks during early adolescence and adulthood, respectively. Conclusion: While early decliners had the most severe CF lung disease, middle and late decliners lost more lung function. Higher social-environmental adversity associated with increased risk of rapid decline and mortality during young adulthood among middle decliners. This sub-phenotype may benefit from enhanced lung-function monitoring and personalized secondary environmental health interventions to mitigate chemical and non-chemical stressors.
RESUMO
BACKGROUND: The extent to which environmental exposures and community characteristics of the built environment collectively predict rapid lung function decline, during adolescence and early adulthood in cystic fibrosis (CF), has not been examined. OBJECTIVE: To identify built environment characteristics predictive of rapid CF lung function decline. METHODS: We performed a retrospective, single-center, longitudinal cohort study (n = 173 individuals with CF aged 6-20 years, 2012-2017). We used a stochastic model to predict lung function, measured as forced expiratory volume in 1 s (FEV1 ) of % predicted. Traditional demographic/clinical characteristics were evaluated as predictors. Built environmental predictors included exposure to elemental carbon attributable to traffic sources (ECAT), neighborhood material deprivation (poverty, education, housing, and healthcare access), greenspace near the home, and residential drivetime to the CF center. MEASUREMENTS AND MAIN RESULTS: The final model, which included ECAT, material deprivation index, and greenspace, alongside traditional demographic/clinical predictors, significantly improved fit and prediction, compared with only demographic/clinical predictors (Likelihood Ratio Test statistic: 26.78, p < 0.0001; the difference in Akaike Information Criterion: 15). An increase of 0.1 µg/m3 of ECAT was associated with 0.104% predicted/yr (95% confidence interval: 0.024, 0.183) more rapid decline. Although not statistically significant, material deprivation was similarly associated (0.1-unit increase corresponded to additional decline of 0.103% predicted/year [-0.113, 0.319]). High-risk regional areas of rapid decline and age-related heterogeneity were identified from prediction mapping. CONCLUSION: Traffic-related air pollution exposure is an important predictor of rapid pulmonary decline that, coupled with community-level material deprivation and routinely collected demographic/clinical characteristics, enhance CF prognostication and enable personalized environmental health interventions.
Assuntos
Fibrose Cística , Adolescente , Humanos , Adulto , Estudos Longitudinais , Estudos Retrospectivos , Estudos de Coortes , Pulmão , Volume Expiratório ForçadoRESUMO
The electronic Medical Records and Genomics (eMERGE) Network assessed the feasibility of deploying portable phenotype rule-based algorithms with natural language processing (NLP) components added to improve performance of existing algorithms using electronic health records (EHRs). Based on scientific merit and predicted difficulty, eMERGE selected six existing phenotypes to enhance with NLP. We assessed performance, portability, and ease of use. We summarized lessons learned by: (1) challenges; (2) best practices to address challenges based on existing evidence and/or eMERGE experience; and (3) opportunities for future research. Adding NLP resulted in improved, or the same, precision and/or recall for all but one algorithm. Portability, phenotyping workflow/process, and technology were major themes. With NLP, development and validation took longer. Besides portability of NLP technology and algorithm replicability, factors to ensure success include privacy protection, technical infrastructure setup, intellectual property agreement, and efficient communication. Workflow improvements can improve communication and reduce implementation time. NLP performance varied mainly due to clinical document heterogeneity; therefore, we suggest using semi-structured notes, comprehensive documentation, and customization options. NLP portability is possible with improved phenotype algorithm performance, but careful planning and architecture of the algorithms is essential to support local customizations.
Assuntos
Registros Eletrônicos de Saúde , Processamento de Linguagem Natural , Genômica , Algoritmos , FenótipoRESUMO
AIM: To predict ambulatory status and Gross Motor Function Classification System (GMFCS) levels in patients with cerebral palsy (CP) by applying natural language processing (NLP) to electronic health record (EHR) clinical notes. METHOD: Individuals aged 8 to 26 years with a diagnosis of CP in the EHR between January 2009 and November 2020 (~12 years of data) were included in a cross-sectional retrospective cohort of 2483 patients. The cohort was divided into train-test and validation groups. Positive predictive value, sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated for prediction of ambulatory status and GMFCS levels. RESULTS: The median age was 15 years (interquartile range 10-20 years) for the total cohort, with 56% being male and 75% White. The validation group resulted in 70% sensitivity, 88% specificity, 81% positive predictive value, and 0.89 AUC for predicting ambulatory status. NLP applied to the EHR differentiated between GMFCS levels I-II and III (15% sensitivity, 96% specificity, 46% positive predictive value, and 0.71 AUC); and IV and V (81% sensitivity, 51% specificity, 70% positive predictive value, and 0.75 AUC). INTERPRETATION: NLP applied to the EHR demonstrated excellent differentiation between ambulatory and non-ambulatory status, and good differentiation between GMFCS levels I-II and III, and IV and V. Clinical use of NLP may help to individualize functional characterization and management. WHAT THIS PAPER ADDS: Natural language processing (NLP) applied to the electronic health record (EHR) can predict ambulatory status in children with cerebral palsy (CP). NLP provides good prediction of Gross Motor Function Classification System level in children with CP using the EHR. NLP methods described could be integrated in an EHR system to provide real-time information.
Assuntos
Paralisia Cerebral , Criança , Humanos , Masculino , Adolescente , Adulto Jovem , Adulto , Feminino , Paralisia Cerebral/complicações , Paralisia Cerebral/diagnóstico , Processamento de Linguagem Natural , Estudos Retrospectivos , Estudos Transversais , Registros Eletrônicos de SaúdeRESUMO
BACKGROUND: Artificial intelligence (AI) technologies, such as machine learning and natural language processing, have the potential to provide new insights into complex health data. Although powerful, these algorithms rarely move from experimental studies to direct clinical care implementation. OBJECTIVE: We aimed to describe the key components for successful development and integration of two AI technology-based research pipelines for clinical practice. METHODS: We summarized the approach, results, and key learnings from the implementation of the following two systems implemented at a large, tertiary care children's hospital: (1) epilepsy surgical candidate identification (or epilepsy ID) in an ambulatory neurology clinic; and (2) an automated clinical trial eligibility screener (ACTES) for the real-time identification of patients for research studies in a pediatric emergency department. RESULTS: The epilepsy ID system performed as well as board-certified neurologists in identifying surgical candidates (with a sensitivity of 71% and positive predictive value of 77%). The ACTES system decreased coordinator screening time by 12.9%. The success of each project was largely dependent upon the collaboration between machine learning experts, research and operational information technology professionals, longitudinal support from clinical providers, and institutional leadership. CONCLUSIONS: These projects showcase novel interactions between machine learning recommendations and providers during clinical care. Our deployment provides seamless, real-time integration of AI technology to provide decision support and improve patient care.
RESUMO
PURPOSE: The variable expressivity and multisystem features of Noonan syndrome (NS) make it difficult for patients to obtain a timely diagnosis. Genetic testing can confirm a diagnosis, but underdiagnosis is prevalent owing to a lack of recognition and referral for testing. Our study investigated the utility of using electronic health records (EHRs) to identify patients at high risk of NS. METHODS: Using diagnosis texts extracted from Cincinnati Children's Hospital's EHR database, we constructed deep learning models from 162 NS cases and 16,200 putative controls. Performance was evaluated on 2 independent test sets, one containing patients with NS who were previously diagnosed and the other containing patients with undiagnosed NS. RESULTS: Our novel method performed significantly better than the previous method, with the convolutional neural network model achieving the highest area under the precision-recall curve in both test sets (diagnosed: 0.43, undiagnosed: 0.16). CONCLUSION: The results suggested the validity of using text-based deep learning methods to analyze EHR and showed the value of this approach as a potential tool to identify patients with features of rare diseases. Given the paucity of medical geneticists, this has the potential to reduce disease underdiagnosis by prioritizing patients who will benefit most from a genetics referral.
Assuntos
Aprendizado Profundo , Síndrome de Noonan , Humanos , Criança , Registros Eletrônicos de Saúde , Síndrome de Noonan/diagnóstico , Síndrome de Noonan/genética , Bases de Dados Factuais , Testes GenéticosRESUMO
Weight entry errors can cause significant patient harm in pediatrics due to pervasive weight-based dosing practices. While computerized algorithms can assist in error detection, they have not achieved high sensitivity and specificity to be further developed as a clinical decision support tool. To train an advanced algorithm, expert-annotated weight errors are essential but difficult to collect. In this study, we developed a visual annotation tool to gather large amounts of expertly annotated pediatric weight charts and conducted a formal user-centered evaluation. Key features of the tool included configurable grid sizes and annotation styles. The user feedback was collected through a structured survey and user clicks on the interface. The results show that the visual annotation tool has high usability (average SUS=86.4). Different combinations of the key features, however, did not significantly improve the annotation efficiency and duration. We have used this tool to collect expert annotations for algorithm development and benchmarking.
Assuntos
Sistemas de Apoio a Decisões Clínicas , Pediatria , Algoritmos , Criança , Retroalimentação , HumanosRESUMO
BACKGROUND: Pediatric heart transplant (PHT) patients have the highest waitlist mortality of solid organ transplants, yet more than 40% of viable hearts are unutilized. A tool for risk prediction could impact these outcomes. This study aimed to compare and validate the PHT risk score models (RSMs) in the literature. METHODS: The literature was reviewed to identify RSMs published. The United Network for Organ Sharing (UNOS) registry was used to validate the published models identified in a pediatric cohort (<18 years) transplanted between 2017 and 2019 and compared against the Scientific Registry of Transplant Recipients (SRTR) 2021 model. Primary outcome was post-transplant 1-year mortality. Odds ratios were obtained to evaluate the association between risk score groups and 1-year mortality. Area under the curve (AUC) was used to compare the RSM scores on their goodness-of-fit, using Delong's test. RESULTS: Six recipient and one donor RSMs published between 2008 and 2021 were included in the analysis. The validation cohort included 1,003 PHT. Low-risk groups had a significantly better survival than high-risk groups as predicted by Choudhry (OR = 4.59, 95% CI [2.36-8.93]) and Fraser III (3.17 [1.43-7.05]) models. Choudhry's and SRTR models achieved the best overall performance (AUC = 0.69 and 0.68, respectively). When adjusted for CHD and ventricular assist device support, all models reported better predictability [AUC > 0.6]. Choudhry (AUC = 0.69) and SRTR (AUC = 0.71) remained the best predicting RSMs even after adjustment. CONCLUSION: Although the RSMs by SRTR and Choudhry provided the best prediction for 1-year mortality, none demonstrated a strong (AUC ≥ 0.8) concordance statistic. All published studies lacked advanced analytical approaches and were derived from an inherently limited dataset.
Assuntos
Transplante de Coração , Criança , Humanos , Sistema de Registros , Fatores de Risco , Doadores de Tecidos , Transplantados , Listas de EsperaRESUMO
BACKGROUND: In critically ill infants, the position of a peripherally inserted central catheter (PICC) must be confirmed frequently, as the tip may move from its original position and run the risk of hyperosmolar vascular damage or extravasation into surrounding spaces. Automated detection of PICC tip position holds great promise for alerting bedside clinicians to noncentral PICCs. OBJECTIVES: This research seeks to use natural language processing (NLP) and supervised machine learning (ML) techniques to predict PICC tip position based primarily on text analysis of radiograph reports from infants with an upper extremity PICC. METHODS: Radiographs, containing a PICC line in infants under 6 months of age, were manually classified into 12 anatomical locations based on the radiologist's textual report of the PICC line's tip. After categorization, we performed a 70/30 train/test split and benchmarked the performance of seven different (neural network, support vector machine, the naïve Bayes, decision tree, random forest, AdaBoost, and K-nearest neighbors) supervised ML algorithms. After optimization, we calculated accuracy, precision, and recall of each algorithm's ability to correctly categorize the stated location of the PICC tip. RESULTS: A total of 17,337 radiographs met criteria for inclusion and were labeled manually. Interrater agreement was 99.1%. Support vector machines and neural networks yielded accuracies as high as 98% in identifying PICC tips in central versus noncentral position (binary outcome) and accuracies as high as 95% when attempting to categorize the individual anatomical location (12-category outcome). CONCLUSION: Our study shows that ML classifiers can automatically extract the anatomical location of PICC tips from radiology reports. Two ML classifiers, support vector machine (SVM) and a neural network, obtained top accuracies in both binary and multiple category predictions. Implementing these algorithms in a neonatal intensive care unit as a clinical decision support system may help clinicians address PICC line position.
Assuntos
Cateterismo Venoso Central , Radiologia , Teorema de Bayes , Catéteres , Humanos , Lactente , Recém-Nascido , Aprendizado de Máquina , Estudos RetrospectivosRESUMO
BACKGROUND: Day-of-surgery cancellation (DoSC) represents a substantial wastage of hospital resources and can cause significant inconvenience to patients and families. Cancellation is reported to impact between 2% and 20% of the 50 million procedures performed annually in American hospitals. Up to 85% of cancellations may be amenable to the modification of patients' and families' behaviors. However, the factors underlying DoSC and the barriers experienced by families are not well understood. OBJECTIVE: This study aims to conduct a geospatial analysis of patient-specific variables from electronic health records (EHRs) of Cincinnati Children's Hospital Medical Center (CCHMC) and of Texas Children's Hospital (TCH), as well as linked socioeconomic factors measured at the census tract level, to understand potential underlying contributors to disparities in DoSC rates across neighborhoods. METHODS: The study population included pediatric patients who underwent scheduled surgeries at CCHMC and TCH. A 5-year data set was extracted from the CCHMC EHR, and addresses were geocoded. An equivalent set of data >5.7 years was extracted from the TCH EHR. Case-based data related to patients' health care use were aggregated at the census tract level. Community-level variables were extracted from the American Community Survey as surrogates for patients' socioeconomic and minority status as well as markers of the surrounding context. Leveraging the selected variables, we built spatial models to understand the variation in DoSC rates across census tracts. The findings were compared to those of the nonspatial regression and deep learning models. Model performance was evaluated from the root mean squared error (RMSE) using nested 10-fold cross-validation. Feature importance was evaluated by computing the increment of the RMSE when a single variable was shuffled within the data set. RESULTS: Data collection yielded sets of 463 census tracts at CCHMC (DoSC rates 1.2%-12.5%) and 1024 census tracts at TCH (DoSC rates 3%-12.2%). For CCHMC, an L2-normalized generalized linear regression model achieved the best performance in predicting all-cause DoSC rate (RMSE 1.299%, 95% CI 1.21%-1.387%); however, its improvement over others was marginal. For TCH, an L2-normalized generalized linear regression model also performed best (RMSE 1.305%, 95% CI 1.257%-1.352%). All-cause DoSC rate at CCHMC was predicted most strongly by previous no show. As for community-level data, the proportion of African American inhabitants per census tract was consistently an important predictor. In the Texas area, the proportion of overcrowded households was salient to DoSC rate. CONCLUSIONS: Our findings suggest that geospatial analysis offers potential for use in targeting interventions for census tracts at a higher risk of cancellation. Our study also demonstrates the importance of home location, socioeconomic disadvantage, and racial minority status on the DoSC of children's surgery. The success of future efforts to reduce cancellation may benefit from taking social, economic, and cultural issues into account.
Assuntos
Grupos Minoritários , Características de Residência , Criança , Registros Eletrônicos de Saúde , Hospitais Pediátricos , Humanos , Fatores SocioeconômicosRESUMO
This study develops a comprehensive method to assess seasonal influences on a longitudinal marker and compare estimates between cohorts. The method extends existing approaches by (i) combining a sine-cosine model of seasonality with a specialized covariance function for modeling longitudinal correlation; (ii) performing mediation analysis on a seasonality model. An example dataset and R code are provided. The bundle of methods is referred to as seasonality, mediation and comparison (SMAC). The case study described utilizes lung function as the marker observed on a cystic fibrosis cohort but SMAC can be used to evaluate other markers and in other disease contexts. Key aspects of customization are as follows.â¢This study introduces a novel seasonality model to fit trajectories of lung function decline and demonstrates how to compare this model to a conventional model in this context.â¢Steps required for mediation analyses in the seasonality model are shown.â¢The necessary calculations to compare seasonality models between cohorts, based on estimation coefficients, are derived in the study.
RESUMO
OBJECTIVE: Substance use screening in adolescence is unstandardized and often documented in clinical notes, rather than in structured electronic health records (EHRs). The objective of this study was to integrate logic rules with state-of-the-art natural language processing (NLP) and machine learning technologies to detect substance use information from both structured and unstructured EHR data. MATERIALS AND METHODS: Pediatric patients (10-20 years of age) with any encounter between July 1, 2012, and October 31, 2017, were included (n = 3890 patients; 19 478 encounters). EHR data were extracted at each encounter, manually reviewed for substance use (alcohol, tobacco, marijuana, opiate, any use), and coded as lifetime use, current use, or family use. Logic rules mapped structured EHR indicators to screening results. A knowledge-based NLP system and a deep learning model detected substance use information from unstructured clinical narratives. System performance was evaluated using positive predictive value, sensitivity, negative predictive value, specificity, and area under the receiver-operating characteristic curve (AUC). RESULTS: The dataset included 17 235 structured indicators and 27 141 clinical narratives. Manual review of clinical narratives captured 94.0% of positive screening results, while structured EHR data captured 22.0%. Logic rules detected screening results from structured data with 1.0 and 0.99 for sensitivity and specificity, respectively. The knowledge-based system detected substance use information from clinical narratives with 0.86, 0.79, and 0.88 for AUC, sensitivity, and specificity, respectively. The deep learning model further improved detection capacity, achieving 0.88, 0.81, and 0.85 for AUC, sensitivity, and specificity, respectively. Finally, integrating predictions from structured and unstructured data achieved high detection capacity across all cases (0.96, 0.85, and 0.87 for AUC, sensitivity, and specificity, respectively). CONCLUSIONS: It is feasible to detect substance use screening and results among pediatric patients using logic rules, NLP, and machine learning technologies.
Assuntos
Registros Eletrônicos de Saúde , Transtornos Relacionados ao Uso de Substâncias , Adolescente , Criança , Humanos , Aprendizado de Máquina , Narração , Processamento de Linguagem Natural , Transtornos Relacionados ao Uso de Substâncias/diagnósticoRESUMO
Labeling clinical data from electronic health records (EHR) in health systems requires extensive knowledge of human expert, and painstaking review by clinicians. Furthermore, existing phenotyping algorithms are not uniformly applied across large datasets and can suffer from inconsistencies in case definitions across different algorithms. We describe here quantitative disease risk scores based on almost unsupervised methods that require minimal input from clinicians, can be applied to large datasets, and alleviate some of the main weaknesses of existing phenotyping algorithms. We show applications to phenotypic data on approximately 100,000 individuals in eMERGE, and focus on several complex diseases, including Chronic Kidney Disease, Coronary Artery Disease, Type 2 Diabetes, Heart Failure, and a few others. We demonstrate that relative to existing approaches, the proposed methods have higher prediction accuracy, can better identify phenotypic features relevant to the disease under consideration, can perform better at clinical risk stratification, and can identify undiagnosed cases based on phenotypic features available in the EHR. Using genetic data from the eMERGE-seq panel that includes sequencing data for 109 genes on 21,363 individuals from multiple ethnicities, we also show how the new quantitative disease risk scores help improve the power of genetic association studies relative to the standard use of disease phenotypes. The results demonstrate the effectiveness of quantitative disease risk scores derived from rich phenotypic EHR databases to provide a more meaningful characterization of clinical risk for diseases of interest beyond the prevalent binary (case-control) classification.
RESUMO
Cytolytic T-cells play an essential role in the adaptive immune system by seeking out, binding and killing cells that present foreign antigens on their surface. An improved understanding of T-cell immunity will greatly aid in the development of new cancer immunotherapies and vaccines for life-threatening pathogens. Central to the design of such targeted therapies are computational methods to predict non-native peptides to elicit a T-cell response, however, we currently lack accurate immunogenicity inference methods. Another challenge is the ability to accurately simulate immunogenic peptides for specific human leukocyte antigen alleles, for both synthetic biological applications, and to augment real training datasets. Here, we propose a beta-binomial distribution approach to derive peptide immunogenic potential from sequence alone. We conducted systematic benchmarking of five traditional machine learning (ElasticNet, K-nearest neighbors, support vector machine, Random Forest and AdaBoost) and three deep learning models (convolutional neural network (CNN), Residual Net and graph neural network) using three independent prior validated immunogenic peptide collections (dengue virus, cancer neoantigen and SARS-CoV-2). We chose the CNN as the best prediction model, based on its adaptivity for small and large datasets and performance relative to existing methods. In addition to outperforming two highly used immunogenicity prediction algorithms, DeepImmuno-CNN correctly predicts which residues are most important for T-cell antigen recognition and predicts novel impacts of SARS-CoV-2 variants. Our independent generative adversarial network (GAN) approach, DeepImmuno-GAN, was further able to accurately simulate immunogenic peptides with physicochemical properties and immunogenicity predictions similar to that of real antigens. We provide DeepImmuno-CNN as source code and an easy-to-use web interface.
Assuntos
COVID-19/imunologia , Peptídeos/imunologia , SARS-CoV-2/imunologia , Algoritmos , COVID-19/virologia , Aprendizado Profundo , Humanos , Aprendizado de Máquina , Redes Neurais de Computação , Peptídeos/genética , SARS-CoV-2/genética , SARS-CoV-2/patogenicidade , Software , Linfócitos T/imunologia , Linfócitos T/virologiaRESUMO
Characterizing seasonal trend in lung function in individuals with chronic lung disease may lead to timelier treatment of acute respiratory symptoms and more precise distinction between seasonal exposures and variability. Limited research has been conducted to assess localized seasonal fluctuation in lung function decline in individuals with cystic fibrosis (CF) in context with routinely collected demographic and clinical data. We conducted a longitudinal cohort study of 253 individuals aged 6-22 years with CF receiving care at a pediatric Midwestern US CF center with median (range) of follow-up time of 4.7 (0-9.95) years, implementing two distinct models to estimate seasonality effects. The outcome, lung function, was measured as percent-predicted of forced expiratory volume in 1 second (FEV1). Both models showed that older age, being male, using Medicaid insurance and having Pseudomonas aeruginosa infection corresponded to accelerated FEV1 decline. A sine wave model for seasonality had better fit to the data, compared to a linear model with categories for seasonality. Compared to international cohorts, seasonal fluctuations occurred earlier and with greater volatility, even after adjustment for ambient temperature. Average lung function peaked in February and dipped in August, and FEV1 fluctuation was 0.81 % predicted (95% CI: 0.52 to 1.1). Adjusting for temperature shifted the peak and dip to March and September, respectively, and decreased FEV1 fluctuation to 0.45 % predicted (95% CI: 0.08 to 0.82). Understanding localized seasonal variation and its impact on lung function may allow researchers to perform precision public health for lung diseases and disorders at the point-of-care level.
Assuntos
Fibrose Cística , Estações do Ano , Adolescente , Criança , Fibrose Cística/epidemiologia , Volume Expiratório Forçado , Humanos , Estudos Longitudinais , Pulmão , Masculino , Meio-Oeste dos Estados Unidos/epidemiologia , Adulto JovemRESUMO
Inaccurate body weight measures can cause critical safety events in clinical settings as well as hindering utilization of clinical data for retrospective research. This study focused on developing a machine learning-based automated weight abnormality detector (AWAD) to analyze growth dynamics in pediatric weight charts and detect abnormal weight values. In two reference-standard based evaluation of real-world clinical data, the machine learning models showed good capacity for detecting weight abnormalities and they significantly outperformed the methods proposed in literature (p-value<0.05). A deep learning model with bi-directional long short-term memory networks achieved the best predictive performance, with AUCs ≥0.989 across the two datasets. The positive predictive value and sensitivity achieved by the system suggested more than 98% screening effort reduction potential in weight abnormality detection. Consequently, we hypothesize that the AWAD, when fully deployed, holds great potential to facilitate clinical research and healthcare delivery that rely on accurate and reliable weight measures.
Assuntos
Aprendizado de Máquina , Criança , Humanos , Valor Preditivo dos Testes , Estudos RetrospectivosRESUMO
BACKGROUND: As a result of the overwhelming proportion of medication errors occurring each year, there has been an increased focus on developing medication error prevention strategies. Recent advances in electronic health record (EHR) technologies allow institutions the opportunity to identify medication administration error events in real time through computerized algorithms. MED.Safe, a software package comprising medication discrepancy detection algorithms, was developed to meet this need by performing an automated comparison of medication orders to medication administration records (MARs). In order to demonstrate generalizability in other care settings, software such as this must be tested and validated in settings distinct from the development site. OBJECTIVE: The purpose of this study is to determine the portability and generalizability of the MED.Safe software at a second site by assessing the performance and fit of the algorithms through comparison of discrepancy rates and other metrics across institutions. METHODS: The MED.Safe software package was executed on medication use data from the implementation site to generate prescribing ratios and discrepancy rates. A retrospective analysis of medication prescribing and documentation patterns was then performed on the results and compared to those from the development site to determine the algorithmic performance and fit. Variance in performance from the development site was further explored and characterized. RESULTS: Compared to the development site, the implementation site had lower audit/order ratios and higher MAR/(order + audit) ratios. The discrepancy rates on the implementation site were consistently higher than those from the development site. Three drivers for the higher discrepancy rates were alternative clinical workflow using orders with dosing ranges; a data extract, transfer, and load issue causing modified order data to overwrite original order values in the EHRs; and delayed EHR documentation of verbal orders. Opportunities for improvement were identified and applied using a software update, which decreased false-positive discrepancies and improved overall fit. CONCLUSIONS: The execution of MED.Safe at a second site was feasible and effective in the detection of medication administration discrepancies. A comparison of medication ordering, administration, and discrepancy rates identified areas where MED.Safe could be improved through customization. One modification of MED.Safe through deployment of a software update improved the overall algorithmic fit at the implementation site. More flexible customizations to accommodate different clinical practice patterns could improve MED.Safe's fit at new sites.
RESUMO
BACKGROUND: At present, electronic health records (EHRs) are the central focus of clinical informatics given their role as the primary source of clinical data. Despite their granularity, the EHR data heavily rely on manual input and are prone to human errors. Many other sources of data exist in the clinical setting, including digital medical devices such as smart infusion pumps. When incorporated with prescribing data from EHRs, smart pump records (SPRs) are capable of shedding light on actions that take place during the medication use process. However, harmoniz-ing the 2 sources is hindered by multiple technical challenges, and the data quality and utility of SPRs have not been fully realized. OBJECTIVE: This study aims to evaluate the quality and utility of SPRs incorporated with EHR data in detecting medication administration errors. Our overarching hypothesis is that SPRs would contribute unique information in the med-ication use process, enabling more comprehensive detection of discrepancies and potential errors in medication administration. METHODS: We evaluated the medication use process of 9 high-risk medications for patients admitted to the neonatal inten-sive care unit during a 1-year period. An automated algorithm was developed to align SPRs with their medica-tion orders in the EHRs using patient ID, medication name, and timestamp. The aligned data were manually re-viewed by a clinical research coordinator and 2 pediatric physicians to identify discrepancies in medication ad-ministration. The data quality of SPRs was assessed with the proportion of information that was linked to valid EHR orders. To evaluate their utility, we compared the frequency and severity of discrepancies captured by the SPR and EHR data, respectively. A novel concordance assessment was also developed to understand the detec-tion power and capabilities of SPR and EHR data. RESULTS: Approximately 70% of the SPRs contained valid patient IDs and medication names, making them feasible for data integration. After combining the 2 sources, the investigative team reviewed 2307 medication orders with 10,575 medication administration records (MARs) and 23,397 SPRs. A total of 321 MAR and 682 SPR dis-crepancies were identified, with vasopressors showing the highest discrepancy rates, followed by narcotics and total parenteral nutrition. Compared with EHR MARs, substantial dosing discrepancies were more commonly detectable using the SPRs. The concordance analysis showed little overlap between MAR and SPR discrepan-cies, with most discrepancies captured by the SPR data. CONCLUSIONS: We integrated smart infusion pump information with EHR data to analyze the most error-prone phases of the medication lifecycle. The findings suggested that SPRs could be a more reliable data source for medication error detection. Ultimately, it is imperative to integrate SPR information with EHR data to fully detect and mitigate medication administration errors in the clinical setting.
RESUMO
INTRODUCTION: School violence has a far-reaching effect, impacting the entire school population including staff, students and their families. Among youth attending the most violent schools, studies have reported higher dropout rates, poor school attendance, and poor scholastic achievement. It was noted that the largest crime-prevention results occurred when youth at elevated risk were given an individualized prevention program. However, much work is needed to establish an effective approach to identify at-risk subjects. OBJECTIVE: In our earlier research, we developed a risk assessment program to interview subjects, identify risk and protective factors, and evaluate risk for school violence. This study focused on developing natural language processing (NLP) and machine learning technologies to automate the risk assessment process. MATERIAL AND METHODS: We prospectively recruited 131 students with or without behavioral concerns from 89 schools between 05/01/2015 and 04/30/2018. The subjects were interviewed with two risk assessment scales and a questionnaire, and their risk of violence were determined by pediatric psychiatrists based on clinical judgment. Using NLP technologies, different types of linguistic features were extracted from the interview content. Machine learning classifiers were then applied to predict risk of school violence for individual subjects. A two-stage feature selection was implemented to identify violence-related predictors. The performance was validated on the psychiatrist-generated reference standard of risk levels, where positive predictive value (PPV), sensitivity (SEN), negative predictive value (NPV), specificity (SPEC) and area under the ROC curve (AUC) were assessed. RESULTS: Compared to subjects' sociodemographic information, use of linguistic features significantly improved classifiers' predictive performance (P < 0.01). The best-performing classifier with n-gram features achieved 86.5 %/86.5 %/85.7 %/85.7 %/94.0 % (PPV/SEN/NPV/SPEC/AUC) on the cross-validation set and 83.3 %/93.8 %/91.7 %/78.6 %/94.6 % (PPV/SEN/NPV/SPEC/AUC) on the test data. The feature selection process identified a set of predictors covering the discussion of subjects' thoughts, perspectives, behaviors, individual characteristics, peers and family dynamics, and protective factors. CONCLUSIONS: By analyzing the content from subject interviews, the NLP and machine learning algorithms showed good capacity for detecting risk of school violence. The feature selection uncovered multiple warning markers that could deliver useful clinical insights to assist personalizing intervention. Consequently, the developed approach offered the promise of an accurate and scalable computerized screening service for preventing school violence.
Assuntos
Algoritmos , Aprendizado de Máquina , Processamento de Linguagem Natural , Medição de Risco/métodos , Estudantes/psicologia , Violência/psicologia , Violência/tendências , Adolescente , Criança , Feminino , Humanos , Masculino , Estudos Prospectivos , Inquéritos e QuestionáriosRESUMO
INTRODUCTION: Natural, social, and constructed environments play a critical role in the development and exacerbation of respiratory diseases. However, less is known regarding the influence of these environmental/community risk factors on the health of individuals living with cystic fibrosis (CF), compared to other pulmonary disorders. AREAS COVERED: Here, we review current knowledge of environmental exposures related to CF, which suggests that environmental/community risk factors do interact with the respiratory tract to affect outcomes. Studies discussed in this review were identified in PubMed between March 2019 and March 2020. Although the limited data available do not suggest that avoiding potentially detrimental exposures other than secondhand smoke could improve outcomes, additional research incorporating novel markers of environmental exposures and community characteristics obtained at localized levels is needed. EXPERT OPINION: As we outline, some environmental exposures and community characteristics are modifiable; if not by the individual, then by policy. We recommend a variety of strategies to advance understanding of environmental influences on CF disease progression.