RESUMEN

Objective: The study aims to identify distinct population-specific comorbidity progression patterns, timely detect potential comorbidities, and gain better understanding of the progression of comorbid conditions among patients. Methods: This work presents a comorbidity progression analysis framework that utilizes temporal comorbidity networks (TCN) for patient stratification and comorbidity prediction. We propose a TCN construction approach that utilizes longitudinal, temporal diagnosis data of patients to construct their TCN. Subsequently, we employ the TCN for patient stratification by conducting preliminary analysis, and typical prescription analysis to uncover potential comorbidity progression patterns in different patient groups. Finally, we propose an innovative comorbidity prediction method by utilizing the distance-matched temporal comorbidity network (TCN-DM). This method identifies similar patients with disease prevalence and disease transition patterns and combines their diagnosis information with that of the current patient to predict potential comorbidity at the patient's next visit. Results: This study validated the capability of the framework using a real-world dataset MIMIC-III, with heart failure (HF) as interested disease to investigate comorbidity progression in HF patients. With TCN, this study can identify four significant distinctive HF subgroups, revealing the progression of comorbidities in patients. Furthermore, compared to other methods, TCN-DM demonstrated better predictive performance with F1-Score values ranging from 0.454 to 0.612, showcasing its superiority. Conclusions: This study can identify comorbidity patterns for individuals and population, and offer promising prediction for future comorbidity developments in patients.

RESUMEN

Accurate prediction of gastric cancer patient survival time is essential for clinical decision-making. However, unified static models lack specificity and flexibility in predictions owing to the varying survival outcomes among gastric cancer patients. We address these problems by using an ensemble learning approach and adaptively assigning greater weights to similar patients to make more targeted predictions when predicting an individual's survival time. We treat these problems as regression problems and introduce a weighted dynamic ensemble regression framework. To better identify similar patients, we devise a method to measure patient similarity, considering the diverse impacts of features. Subsequently, we use this measure to design both a weighted K-means clustering method and a fuzzy K-means sampling technique to group patients and train corresponding base regressors. To achieve more targeted predictions, we calculate the weight of each base regressor based on the similarity between the patient to be predicted and the patient clusters, culminating in the integration of the results. The model is validated on a dataset of 7791 patients, outperforming other models in terms of three evaluation metrics, namely, the root mean square error, mean absolute error, and the coefficient of determination. The weighted dynamic ensemble regression strategy can improve the baseline model by 1.75%, 2.12%, and 13.45% in terms of the three respective metrics while also mitigating the imbalanced survival time distribution issue. This enhanced performance has been statistically validated, even when tested on six public datasets with different sizes. By considering feature variations, patients with distinct survival profiles can be effectively differentiated, and the model predictive performance can be enhanced. The results generated by our proposed model can be invaluable in guiding decisions related to treatment plans and resource allocation. Furthermore, the model has the potential for broader applications in prognosis for other types of cancers or similar regression problems in various domains.

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVE: Mortality prediction is an important task in intensive care unit (ICU) for quantifying the severity of patients' physiological condition. Currently, scoring systems are widely applied for mortality prediction, while the performance is unsatisfactory in many clinical conditions due to the non-specificity and linearity characteristics of the used model. As the availability of the large volume of data recorded in electronic health records (EHRs), deep learning models have achieved state-of-art predictive performance. However, deep learning models are hard to meet the requirement of explainability in clinical conditions. Hence, an explainable Knowledge Distillation method with XGBoost (XGB-KD) is proposed to improve the predictive performance of XGBoost while supporting better explainability. METHODS: In this method, we first use outperformed deep learning teacher models to learn the complex patterns hidden in high-dimensional multivariate time series data. Then, we distill knowledge from soft labels generated by the ensemble of teacher models to guide the training of XGBoost student model, whose inputs are meaningful features obtained from feature engineering. Finally, we conduct model calibration to obtain predicted probabilities reflecting the true posterior probabilities and use SHapley Additive exPlanations (SHAP) to obtain insights about the trained model. RESULTS: We conduct comprehensive experiments on MIMIC-III dataset to evaluate our method. The results demonstrate that our method achieves better predictive performance than vanilla XGBoost, deep learning models and several state-of-art baselines from related works. Our method can also provide intuitive explanations. CONCLUSIONS: Our method is useful for improving the predictive performance of XGBoost by distilling knowledge from deep learning models and can provide meaningful explanations for predictions.

Asunto(s)

RESUMEN

In recent years, multiview learning technologies have attracted a surge of interest in the machine learning domain. However, when facing complex and diverse applications, most multiview learning methods mainly focus on specific fields rather than provide a scalable and robust proposal for different tasks. Moreover, most conventional methods used in these tasks are based on single view, which cannot be readily extended into the multiview scenario. Therefore, how to provide an efficient and scalable multiview framework is very necessary yet full of challenges. Inspired by the fact that most of the existing single view algorithms are graph-based ones to learn the complex structures within given data, this article aims at leveraging most existing graph embedding works into one formula via introducing the graph consensus term and proposes a unified and scalable multiview learning framework, termed graph consensus multiview framework (GCMF). GCMF attempts to make full advantage of graph-based works and rich information in the multiview data at the same time. On one hand, the proposed method explores the graph structure in each view independently to preserve the diversity property of graph embedding methods; on the other hand, learned graphs can be flexibly chosen to construct the graph consensus term, which can more stably explore the correlations among multiple views. To this end, GCMF can simultaneously take the diversity and complementary information among different views into consideration. To further facilitate related research, we provide an implementation of the multiview extension for locality linear embedding (LLE), named GCMF-LLE, which can be efficiently solved by applying the alternating optimization strategy. Empirical validations conducted on six benchmark datasets can show the effectiveness of our proposed method.

RESUMEN

In order to understand the evolution of the diagnosis and treatment plans of corona virus disease 2019 (COVID-19), and provide convenience for medical staff in actual diagnosis and treatment, this paper uses the 9 diagnosis and treatment plans of COVID-19 issued by the National Health Commission during the period from January 26, 2020 to August 19, 2020 as research data to perform comparative analysis and visual analysis. Based on text mining, this paper obtained the text similarity and summarized its evolution law by expressing and measuring the similarity of the overall diagnosis and treatment plans of COVID-19 and the same modules, which provides reference for clinical diagnosis and treatment practice and other diagnosis and treatment plan formulation.

Asunto(s)

RESUMEN

OBJECTIVE: The reasonable classification of a large number of distinct diagnosis codes can clarify patient diagnostic information and help clinicians to improve their ability to assign and target treatment for primary diseases. Our objective is to identify and predict a unifying diagnosis (UD) from electronic medical records (EMRs). METHODS: We screened 4,418 sepsis patients from a public MIMIC-III database and extracted their diagnostic information for UD identification, their demographic information, laboratory examination information, chief complaint, and history of present illness information for UD prediction. We proposed a data-driven UD identification and prediction method (UDIPM) embedding the disease ontology structure. First, we designed a set similarity measure method embedding the disease ontology structure to generate a patient similarity matrix. Second, we applied affinity propagation clustering to divide patients into different clusters, and extracted a typical diagnosis code co-occurrence pattern from each cluster. Furthermore, we identified a UD by fusing visual analysis and a conditional co-occurrence matrix. Finally, we trained five classifiers in combination with feature fusion and feature selection method to unify the diagnosis prediction. RESULTS: The experimental results on a public electronic medical record dataset showed that the UDIPM could extracted a typical diagnosis code co-occurrence pattern effectively, identified and predicted a UD based on patients' diagnostic and admission information, and outperformed other fusion methods overall. CONCLUSIONS: The accurate identification and prediction of the UD from a large number of distinct diagnosis codes and multi-source heterogeneous patient admission information in EMRs can provide a data-driven approach to assist better coding integration of diagnosis.

Asunto(s)

RESUMEN

OBJECTIVE: Electronic Medical Records (EMRs) contain temporal and heterogeneous doctor order information that can be used for treatment pattern discovery. Our objective is to identify "right patient", "right drug", "right dose", "right route", and "right time" from doctor order information. METHODS: We propose a fusion framework to extract typical treatment patterns based on multi-view similarity Network Fusion (SNF) method. The multi-view SNF method involves three similarity measures: content-view similarity, sequence-view similarity and duration-view similarity. An EMR dataset and two metrics were utilized to evaluate the performance and to extract typical treatment patterns. RESULTS: Experimental results on a real-world EMR dataset show that the multi-view similarity network fusion method outperforms all the single-view similarity measures and also outperforms the existing similarity measure methods. Furthermore, we extract and visualize typical treatment patterns by clustering analysis. CONCLUSION: The extracted typical treatment patterns by combining doctor order content, sequence, and duration views can provide data-driven guidelines for artificial intelligence in medicine and help clinicians make better decisions in clinical practice.

Asunto(s)

RESUMEN

BACKGROUND: Clinical prediction tasks such as patient mortality, length of hospital stay, and disease diagnosis are highly important in critical care research. The existing studies for clinical prediction mainly used simple summary statistics to summarize information from physiological time series. However, this lack of statistics leads to a lack of information. In addition, using only maximum and minimum statistics to indicate patient features fails to provide an adequate explanation. Few studies have evaluated which summary statistics best represent physiological time series. METHODS: In this paper, we summarize 14 statistics describing the characteristics of physiological time series, including the central tendency, dispersion tendency, and distribution shape. Then, we evaluate the use of summary statistics of physiological time series as features for three clinical prediction tasks. To find the combinations of statistics that yield the best performances under different tasks, we use a cross-validation-based genetic algorithm to approximate the optimal statistical combination. RESULTS: By experiments using the EHRs of 6,927 patients, we obtained prediction results based on both single statistics and commonly used combinations of statistics under three clinical prediction tasks. Based on the results of an embedded cross-validation genetic algorithm, we obtained 25 optimal sets of statistical combinations and then tested their prediction results. By comparing the performances of prediction with single statistics and commonly used combinations of statistics with quantitative analyses of the optimal statistical combinations, we found that some statistics play central roles in patient representation and different prediction tasks have certain commonalities. CONCLUSION: Through an in-depth analysis of the results, we found many practical reference points that can provide guidance for subsequent related research. Statistics that indicate dispersion tendency, such as min, max, and range, are more suitable for length of stay prediction tasks, and they also provide information for short-term mortality prediction. Mean and quantiles that reflect the central tendency of physiological time series are more suitable for mortality and disease prediction. Skewness and kurtosis perform poorly when used separately for prediction but can be used as supplementary statistics to improve the overall prediction effect.

Asunto(s)

RESUMEN

BACKGROUND: A clinical pathway (CP) defines a standardized care process for a well-defined patient group that aims to improve patient outcomes and promote patient safety. However, the construction of a new pathway from scratch is a time-consuming task for medical staff because it involves many factors, including objects, multidisciplinary collaboration, sequential design, and outcome measurements. Recently, the rapid development of hospital information systems has allowed the storage of large volumes of electronic medical records (EMRs), and this information constitutes an abundant data resource for building CPs using data-mining methods. METHODS: We provide an automatic method for extracting typical treatment processes from EMRs that consists of four key steps. First, a novel similarity method is proposed to measure the similarity of two treatment records. Then, we perform an affinity propagation (AP) clustering algorithm to cluster doctor order set sequences (DOSSs). Next, a framework is proposed to extract a high-level description of each treatment cluster. Finally, we evaluate the extracted typical treatment processes by matching the treatment cluster with external information, such as the treatment efficacy, length of stay, and treatment cost. RESULTS: By experiments on EMRs of 8287 cerebral infarction patients, it is concluded that our proposed method can effectively extract typical treatment processes from treatment records, and also has great potential to improve treatment outcome by personalizing the treatment process for patients with different conditions. CONCLUSION: The extracted typical treatment processes are intuitive and can provide managerial guidance for CP redesign and optimization. In addition, our work can assist clinicians in clearly understanding their routine treatment processes and recommend optimal treatment pathways for patients.

Asunto(s)

RESUMEN

Under the theoretical guidance of "combination of disease and syndrome， correspondence between syndrome and prescription， and dynamic space-time"， 11 135 acute ischemic stroke patients were collected from hospital information system(HIS) of many 3A grade hospitals of traditional Chinese medicine. Complex network analysis was adopted to obtain the core syndrome elements in different periods of acute ischemic stroke patients， and it was found that the core syndrome elements were blood stasis syndrome， phlegm， endogenous wind， Yin deficiency， Qi deficiency， heat， hyperactivity of liver Yang， liver， and kidney of patients in hospital for the first day， and during 8-14 d in hospitalization， the core syndrome elements were blood stasis， phlegm， Yin deficiency， Qi deficiency， endogenous wind， hyperactivity of liver Yang， liver， and kidney. The data with "improved" and "cured" treatment outcomes were adopted for complex network analysis and correlation analysis to identify the Chinese and Western medicine group modules in patients with different disease conditions in different phases after hospitalization. It was found that the Chinese and Western medicine modules within 14 d after hospitalization mainly included "blood-activating and stasis-dissolving module "consisted by "anti-platelet drug + circulation-improving medicine(or anticoagulant drug and anti-fibrinogen drug， et al) + blood-activating and stasis-dissolving drugs"， as well as "stasis-dissolving and phlegm-reducing module" consisted by "anti-platelet drugs + circulation-improving medicine(or anticoagulant drug and anti-fibrinogen drug， et al) + phlegm refreshing drug". The core Chinese and Western medicine modules in patients with urgent and general conditions within 7 d after hospitalization mainly used "blood-activating and stasis-dissolving module" and "stasis-dissolving and phlegm-reducing module". Three or more Chinese medicine and Western medicines module with more than 1% utilization rate was not found in the patients with critical disease condition in admission. The urgent， general and critically ill patients in admission mainly used "blood-activating and stasis-dissolving module" in 8-14 d. From the real world medical big data research， it was found that the combined use of Chinese and Western medicines were consistent with "combination of disease and syndrome， correspondence between syndrome and prescription， and dynamic space-time" theory， and multiple multidimensional dynamic Chinese medicine and Western medicine group modules of "patient-syndrome-drug-time-effective" at the acute ischemic stroke stage were dug out， forming the method of Chinese and Western medicine combination research based on electrical medical big data.

Asunto(s)

RESUMEN

The acute phase of ischemic stroke patients are often treated with both Chinese patent medicine:and western medicine therapies in clinical practice. This research included 27,678 cases of the acute phase of ischemic stroke came from 14 3A level hospitals. We collected data from patients with ischemic stroke who used both Chinese patent medicine and western medicine and were hopitalized within 14 days from hospital information system (HIS). Constructing complex network of Chinese patent medicine and western medicine were found to show scale-free network. Hierarchical structure of the core algorithm was used to analyze the characteristics of combined core Chinese patent medicine and western medicine in admission condition of "acute", "critically", and "general" of ischemic stroke acute phase patient within one day, 2-3 days, 4-7 days and 8-14 days. We found that the core Chinese patent medicine mainly used for activate blood and resolve stasis medicine, and phlegm eliminating brain refreshing medicine in all kinds of patients, but the phlegm eliminating brain refreshing medicine were used to reduce with time elapsing. The core western medicine mainly used for anti-platelet medicine, improve circulation medicine, neuroprotective medicine, anticoagulants medicine and dehydration medicine. The dehydration medicine as the core western medicine for critically patients within 14 days, but the patients for general admission as core western medicine within 3 days. The neuroprotective medicine was used to decreases after 7 days in hospital. Combination of Chinese patent medicine and western medicine were mainly for neuroprotective medicine + activate blood and resolve stasis medicine, and anti-platelet medicine + activate blood and resolve stasis medicine, and improve circulation medicine + activate blood and resolve stasis medicine. The phlegm eliminating brain refreshing medicine was mainly combined with neuroprotective medicine by urgent and general admission condition patients, and it was more combined with dehydration medicine by critically admission condition patients. This research found that the dynamic characteristics for the combination of Chinese patent medicine and western medicine of acute phase of ischemic stroke patients by big data analytics and complex networks modeling, and provide basis for acute phase of ischemic stroke patients, it provide basis for ischemic stroke treatment strategy making.

Asunto(s)