Search

Objectives: This study sought to explore the use of novel natural language processing (NLP) methods for classifying unstructured, qualitative textual data from interviews of patients with cancer to identify patient-reported symptoms and impacts on quality of life.Methods: We tested the ability of 4 NLP models to accurately classify text from interview transcripts as "symptom," "quality of life impact," and "other." Interview data sets from patients with hepatocellular carcinoma (HCC) (n = 25), biliary tract cancer (BTC) (n = 23), and gastric cancer (n = 24) were used. Models were cross-validated with transcript subsets designated for training, validation, and testing. Multiclass classification performance of the 4 models was evaluated at paragraph and sentence level using the HCC testing data set and analyzed by the one-versus-rest technique quantified by the receiver operating characteristic area under the curve (ROC AUC) score.Results: NLP models accurately classified multiclass text from patient interviews. The Bidirectional Encoder Representations from Transformers model generally outperformed all other models at paragraph and sentence level. The highest predictive performance of the Bidirectional Encoder Representations from Transformers model was observed using the HCC data set to train and BTC data set to test (mean ROC AUC, 0.940 [SD 0.028]), with similarly high predictive performance using balanced and imbalanced training data sets from BTC and gastric cancer populations.Conclusions: NLP models were accurate in predicting multiclass classification of text from interviews of patients with cancer, with most surpassing 0.9 ROC AUC at paragraph level. NLP may be a useful tool for scaling up processing of patient interviews in clinical studies and, thus, could serve to facilitate patient input into drug development and improving patient care. [ABSTRACT FROM AUTHOR]

Background: Rainfall patterns are one of the main drivers of dengue transmission as mosquitoes require standing water to reproduce. However, excess rainfall can be disruptive to the Aedes reproductive cycle by “flushing out” aquatic stages from breeding sites. We developed models to predict the occurrence of such “flushing” events from rainfall data and to evaluate the effect of flushing on dengue outbreak risk in Singapore between 2000 and 2016. Methods: We used machine learning and regression models to predict days with “flushing” in the dataset based on entomological and corresponding rainfall observations collected in Singapore. We used a distributed lag nonlinear logistic regression model to estimate the association between the number of flushing events per week and the risk of a dengue outbreak. Results: Days with flushing were identified through the developed logistic regression model based on entomological data (test set accuracy = 92%). Predictions were based upon the aggregate number of thresholds indicating unusually rainy conditions over multiple weeks. We observed a statistically significant reduction in dengue outbreak risk one to six weeks after flushing events occurred. For weeks with five or more flushing events, compared with weeks with no flushing events, the risk of a dengue outbreak in the subsequent weeks was reduced by 16% to 70%. Conclusions: We have developed a high accuracy predictive model associating temporal rainfall patterns with flushing conditions. Using predicted flushing events, we have demonstrated a statistically significant reduction in dengue outbreak risk following flushing, with the time lag well aligned with time of mosquito development from larvae and infection transmission. Vector control programs should consider the effects of hydrological conditions in endemic areas on dengue transmission. [ABSTRACT FROM AUTHOR]

The ability to accurately predict non-small cell lung cancer (NSCLC) patient survival is crucial for informing physician decision-making, and the increasing availability of multi-omics data offers the promise of enhancing prognosis predictions. We present a multimodal integration approach that leverages microRNA, mRNA, DNA methylation, long non-coding RNA (lncRNA) and clinical data to predict NSCLC survival and identify patient subtypes, utilizing denoising autoencoders for data compression and integration. Survival performance for patients with lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) was compared across modality combinations and data integration methods. Using The Cancer Genome Atlas data, our results demonstrate that survival prediction models combining multiple modalities outperform single modality models. The highest performance was achieved with a combination of only two modalities, lncRNA and clinical, at concordance indices (C-indices) of 0.69 ± 0.03 for LUAD and 0.62 ± 0.03 for LUSC. Models utilizing all five modalities achieved mean C-indices of 0.67 ± 0.04 and 0.63 ± 0.02 for LUAD and LUSC, respectively, while the best individual modality performance reached C-indices of 0.64 ± 0.03 for LUAD and 0.59 ± 0.03 for LUSC. Analysis of biological differences revealed two distinct survival subtypes with over 900 differentially expressed transcripts. [ABSTRACT FROM AUTHOR]

The ability to accurately predict non-small cell lung cancer (NSCLC) patient survival is crucial for informing physician decision-making, and the increasing availability of multi-omics data offers the promise of enhancing prognosis predictions. We present a multimodal integration approach that leverages microRNA, mRNA, DNA methylation, long non-coding RNA (lncRNA) and clinical data to predict NSCLC survival and identify patient subtypes, utilizing denoising autoencoders for data compression and integration. Survival performance for patients with lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) was compared across modality combinations and data integration methods. Using The Cancer Genome Atlas data, our results demonstrate that survival prediction models combining multiple modalities outperform single modality models. The highest performance was achieved with a combination of only two modalities, lncRNA and clinical, at concordance indices (C-indices) of 0.69 ± 0.03 for LUAD and 0.62 ± 0.03 for LUSC. Models utilizing all five modalities achieved mean C-indices of 0.67 ± 0.04 and 0.63 ± 0.02 for LUAD and LUSC, respectively, while the best individual modality performance reached C-indices of 0.64 ± 0.03 for LUAD and 0.59 ± 0.03 for LUSC. Analysis of biological differences revealed two distinct survival subtypes with over 900 differentially expressed transcripts. [ABSTRACT FROM AUTHOR]

Understanding the effect of media on disease spread can help improve epidemic forecasting and uncover preventive measures to slow the spread of disease. Most previously introduced models have approximated media effect through disease incidence, making media influence dependent on the size of epidemic. We propose an alternative approach, which relies on real data about disease coverage in the news, allowing us to model low incidence/high interest diseases, such as SARS, Ebola or H1N1. We introduce a network-based model, in which disease is transmitted through local interactions between individuals and the probability of transmission is affected by media coverage. We assume that media attention increases self-protection (e.g. hand washing and compliance with social distancing), which, in turn, decreases disease model. We apply the model to the case of H1N1 transmission in Mexico City in 2009 and show how media influence—measured by the time series of the weekly count of news articles published on the outbreak—helps to explain the observed transmission dynamics. We show that incorporating the media attention based on the observed media coverage of the outbreak better estimates the disease dynamics from what would be predicted by using media function that approximate the media impact using the number of cases and rate of spread. Finally, we apply the model to a typical influenza season in Washington, DC and estimate how the transmission pattern would have changed given different levels of media coverage. [ABSTRACT FROM AUTHOR]

Background: Studies of cost-effective disease prevention have typically focused on the tradeoff between the cost of disease transmission and the cost of applying control measures. We present a novel approach that also accounts for the cost of social disruptions resulting from the spread of disease. These disruptions, which we call social response, can include heightened anxiety, strain on healthcare infrastructure, economic losses, or violence. Methodology: The spread of disease and social response are simulated under several different intervention strategies. The modeled social response depends upon the perceived risk of the disease, the extent of disease spread, and the media involvement. Using Monte Carlo simulation, we estimate the total number of infections and total social response for each strategy. We then identify the strategy that minimizes the expected total cost of the disease, which includes the cost of the disease itself, the cost of control measures, and the cost of social response. Conclusions: The model-based simulations suggest that the least-cost disease control strategy depends upon the perceived risk of the disease, as well as media intervention. The most cost-effective solution for diseases with low perceived risk was to implement moderate control measures. For diseases with higher perceived severity, such as SARS or Ebola, the most cost-effective strategy shifted toward intervening earlier in the outbreak, with greater resources. When intervention elicited increased media involvement, it remained important to control high severity diseases quickly. For moderate severity diseases, however, it became most cost-effective to implement no intervention and allow the disease to run its course. Our simulation results imply that, when diseases are perceived as severe, the costs of social response have a significant influence on selecting the most cost-effective strategy. [ABSTRACT FROM AUTHOR]

The article introduces a joint methodology for predicting an adverse event within temporal data, a collection of observations which is fast-growing in availability. The methodology is based on a combination of supervised learning, in which the target event is known and prediction algorithms are used to build a predictive model from a set of attributes. The application of the methodology in healthcare using medical claims data to predict the risk of myocardial infarction is also discussed.

Background: Predictive models can serve as early warning systems and can be used to forecast future risk of various infectious diseases. Conventionally, regression and time series models are used to forecast dengue incidence, using dengue surveillance (e.g., case counts) and weather data. However, these models may be limited in terms of model assumptions and the number of predictors that can be included. Machine learning (ML) methods are designed to work with a large number of predictors and thus offer an appealing alternative. Here, we compared the performance of ML algorithms with that of regression models in predicting dengue cases and outbreaks from 4 to up to 12 weeks in advance. Many countries lack sufficient health surveillance infrastructure, as such we evaluated the contribution of dengue surveillance and weather data on the predictive power of these models. Methods: We developed ML, regression, and time series models to forecast weekly dengue case counts and outbreaks in Iquitos, Peru; San Juan, Puerto Rico; and Singapore from 1990–2016. Forecasts were generated using available weekly dengue surveillance, and weather data. We evaluated the agreement between model forecasts and actual dengue observations using Mean Absolute Error and Matthew's Correlation Coefficient (MCC). Results: For near term predictions of weekly case counts and when using surveillance data, ML models had 21% and 33% less error than regression and time series models respectively. However, using weather data only, ML models did not demonstrate a practical advantage. When forecasting weekly dengue outbreaks 12 weeks in advance, ML models achieved a maximum MCC of 0.61. Conclusions: Our results identified 2 scenarios when ML models are advantageous over regression model: 1) predicting dengue weekly case counts 4 weeks ahead when dengue surveillance data are available and 2) predicting weekly dengue outbreaks 12 weeks ahead when dengue surveillance data are unavailable. Given the advantages of ML models, dengue early warning systems may be improved by the inclusion of these models. Author summary: Accurate and timely forecasts of dengue fever can help mitigate the impact of the disease. Currently, regression and time series models are frequently used to predict dengue cases and outbreaks. However, these models may be limited in terms of model assumptions and the number of predictors that can be included. Machine learning (ML) models offer an appealing alternative as they have a nonlinear framework and can be applied to high dimensional data. In this study, we compared the performance of ML algorithms with that of regression and time series models in predicting dengue cases and outbreaks from 4 to up to 12 weeks in advance in 3 dengue-endemic regions. Model predictions were based upon local dengue surveillance (e.g., case counts), population, temporal, and weather data. Many countries lack sufficient health surveillance infrastructure, as such we evaluated the contribution of dengue surveillance and weather data on the predictive power of the models. Our results identified 2 scenarios when ML models performed better than conventional models: 1) predicting dengue weekly case counts 4 weeks ahead when dengue surveillance data are available and 2) predicting weekly dengue outbreaks 12 weeks ahead when dengue surveillance data are unavailable. This research suggests that ML models can be a beneficial tool for dengue early warning systems. [ABSTRACT FROM AUTHOR]

In many data classification problems, a number of methods will give similar accuracy. However, when working with people who are not experts in data science such as doctors, lawyers, and judges among others, finding interpretable algorithms can be a critical success factor. Practitioners have a deep understanding of the individual input variables but far less insight into how they interact with each other. For example, there may be ranges of an input variable for which the observed outcome is significantly more or less likely. This paper describes an algorithm for automatic detection of such thresholds, called the Univariate Flagging Algorithm (UFA). The algorithm searches for a separation that optimizes the difference between separated areas while obtaining a high level of support. We evaluate its performance using six sample datasets and demonstrate that thresholds identified by the algorithm align well with published results and known physiological boundaries. We also introduce two classification approaches that use UFA and show that the performance attained on unseen test data is comparable to or better than traditional classifiers when confidence intervals are considered. We identify conditions under which UFA performs well, including applications with large amounts of missing or noisy data, applications with a large number of inputs relative to observations, and applications where incidence of the target is low. We argue that ease of explanation of the results, robustness to missing data and noise, and detection of low incidence adverse outcomes are desirable features for clinical applications that can be achieved with relatively simple classifier, like UFA. [ABSTRACT FROM AUTHOR]

We define a structural property of real-world large-scale communication networks consisting of the recurring patterns of communication among individuals, which we term persistent cascades. Using methods of inexact tree matching and agglomerative clustering, we group these patterns into classes which we claim represent some underlying way in which individuals tend to disseminate information. We extend methods from epidemic modeling to offer a way to analytically model this recurring structure in a random network, and comparing to the data, we find that the real cascading structure is significantly larger and more recurrent than the random model. We find that the cascades reveal a habitual hierarchy of spreading, alternative roles in weekday vs weekend spreading, and the existence of hidden spreaders. Finally, we show that cascade membership increases the likelihood of receiving information spreading through the network through simulation on the real order of communication events. [ABSTRACT FROM AUTHOR]

Infectious disease outbreaks often have consequences beyond human health, including concern among the population, economic instability, and sometimes violence. A warning system capable of anticipating social disruptions resulting from disease outbreaks is urgently needed to help decision makers prepare appropriately. We designed a system that operates in near real-time to identify and predict social response. Over 150,000 Internet-based news articles related to outbreaks of 16 diseases in 72 countries and territories were provided by HealthMap. These articles were automatically tagged with indicators of the disease activity and population reaction. An anomaly detection algorithm was implemented on the population reaction indicators to identify periods of unusually severe social response. Then a model was developed to predict the probability of these periods of unusually severe social response occurring in the coming week, 2 and 3 weeks. This model exhibited remarkably strong performance for diseases with substantial media coverage. For country-disease pairs with a median of 20 or more articles per year, the onset of social response in the next week was correctly predicted over 60% of the time, and 87% of weeks were correctly predicted. Performance was weaker for diseases with little media coverage, and, for these diseases, the main utility of our system is in identifying social response when it occurs, rather than predicting when it will happen in the future. Overall, the developed near real-time prediction approach is a promising step toward developing predictive models to inform responders of the likely social consequences of disease spread. [ABSTRACT FROM AUTHOR]