Application of group LASSO regression based Bayesian networks in risk factors exploration and disease prediction for acute kidney injury in hospitalized patients with hematologic malignancies

Prediction of anticancer drug sensitivity using an interpretable model guided by deep learning

BACKGROUND

The prediction of drug sensitivity plays a crucial role in improving the therapeutic effect of drugs. However, testing the effectiveness of drugs is challenging due to the complex mechanism of drug reactions and the lack of interpretability in most machine learning and deep learning methods. Therefore, it is imperative to establish an interpretable model that receives various cell line and drug feature data to learn drug response mechanisms and achieve stable predictions between available datasets.

RESULTS

This study proposes a new and interpretable deep learning model, DrugGene, which integrates gene expression, gene mutation, gene copy number variation of cancer cells, and chemical characteristics of anticancer drugs to predict their sensitivity. This model comprises two different branches of neural networks, where the first involves a hierarchical structure of biological subsystems that uses the biological processes of human cells to form a visual neural network (VNN) and an interpretable deep neural network for human cancer cells. DrugGene receives genotype input from the cell line and detects changes in the subsystem states. We also employ a traditional artificial neural network (ANN) to capture the chemical structural features of drugs. DrugGene generates final drug response predictions by combining VNN and ANN and integrating their outputs into a fully connected layer. The experimental results using drug sensitivity data extracted from the Cancer Drug Sensitivity Genome Database and the Cancer Treatment Response Portal v2 reveal that the proposed model is better than existing prediction methods. Therefore, our model achieves higher accuracy, learns the reaction mechanisms between anticancer drugs and cell lines from various features, and interprets the model's predicted results.

CONCLUSIONS

Our method utilizes biological pathways to construct neural networks, which can use genotypes to monitor changes in the state of network subsystems, thereby interpreting the prediction results in the model and achieving satisfactory prediction accuracy. This will help explore new directions in cancer treatment. More available code resources can be downloaded for free from GitHub ( https://github.com/pangweixiong/DrugGene ).

Characterization of Risk Prediction Models for Acute Kidney Injury: A Systematic Review and Meta-analysis

Importance

Despite the expansion of published prediction models for acute kidney injury (AKI), there is little evidence of uptake of these models beyond their local derivation nor data on their association with patient outcomes.

Objective

To systematically review published AKI prediction models across all clinical subsettings.

Data Sources

MEDLINE via PubMed (January 1946 to April 2021) and Embase (January 1947 to April 2021) were searched using medical subject headings and text words related to AKI and prediction models.

Study Selection

All studies that developed a prediction model for AKI, defined as a statistical model with at least 2 predictive variables to estimate future occurrence of AKI, were eligible for inclusion. There was no limitation on study populations or methodological designs.

Data Extraction and Synthesis

Two authors independently searched the literature, screened the studies, and extracted and analyzed the data following the Preferred Reporting Items for Systematic Review and Meta-analyses guideline. The data were pooled using a random-effects model, with subgroups defined by 4 clinical settings. Between-study heterogeneity was explored using multiple methods, and funnel plot analysis was used to identify publication bias.

Main Outcomes and Measures

C statistic was used to measure the discrimination of prediction models.

Results

Of the 6955 studies initially identified through literature searching, 150 studies, with 14.4 million participants, met the inclusion criteria. The study characteristics differed widely in design, population, AKI definition, and model performance assessments. The overall pooled C statistic was 0.80 (95% CI, 0.79-0.81), with pooled C statistics in different clinical subsettings ranging from 0.78 (95% CI, 0.75-0.80) to 0.82 (95% CI, 0.78-0.86). Between-study heterogeneity was high overall and in the different clinical settings (eg, contrast medium-associated AKI: I2 = 99.9%; P < .001), and multiple methods did not identify any clear sources. A high proportion of models had a high risk of bias (126 [84.4%]) according to the Prediction Model Risk Of Bias Assessment Tool.

Conclusions and Relevance

In this study, the discrimination of the published AKI prediction models was good, reflected by high C statistics; however, the wide variation in the clinical settings, populations, and predictive variables likely drives the highly heterogenous findings that limit clinical utility. Standardized procedures for development and validation of prediction models are urgently needed.

Machine learning for acute kidney injury: Changing the traditional disease prediction mode

Acute kidney injury (AKI) is a serious clinical comorbidity with clear short-term and long-term prognostic implications for inpatients. The diversity of risk factors for AKI has been recognized in previous studies, and a series of predictive models have been developed using traditional statistical methods in conjunction with its preventability, but they have failed to meet the expectations in limited clinical applications, the rapid spread of electronic health records and artificial intelligence machine learning technology has brought new hope for the construction of AKI prediction models. In this article, we systematically review the definition and classification of machine learning methods, modeling ideas and evaluation methods, and the characteristics and current status of modeling studies. According to the modeling objectives, we subdivided them into critical care medical setting models, all medical environment models, special surgery models, special disease models, and special nephrotoxin exposure models. As the first review article to comprehensively summarize and analyze machine learning prediction models for AKI, we aim to objectively describe the advantages and disadvantages of machine learning approaches to modeling, and help other researchers more quickly and intuitively understand the current status of modeling research, inspire ideas and learn from experience, so as to guide and stimulate more research and more in-depth exploration in the future, which will ultimately provide greater help to improve the overall status of AKI diagnosis and treatment.

The risk assessment of relapse among newly enrolled participants in methadone maintenance treatment: A group-LASSO based Bayesian network study

Background

Relapse is a great barrier to improving the effectiveness of methadone maintenance treatment (MMT). Participants with different treatment durations could vary in their compliance with MMT, which may lead to different levels of relapse risk. This study aims to identify the risk factors for relapse and assess the relapse risk of MMT participants of different treatment durations.

Method

This retrospective study used data collected from seven MMT clinics in Guangdong Province, China, from January 2010 to April 2017. Newly enrolled participants who received 6 (n = 903) and 12 (n = 710) months of consecutive treatment with complete data were included. We selected significant risk factors for relapse through the group lasso regression and then incorporated them into Bayesian networks to reveal relationships between factors and predict the relapse risk.

Results

The results showed that participants who received 6-month treatment had a lower relapse rate (32.0%) than those of 12-month treatment (39.0%, P < 0.05). Factors including personal living status and daily methadone dose were only influential to those who received the 6-month treatment. However, age, age at the initial drug use, HIV infection status, sexual behaviors, and continuous treatment days were common factors of both durations. The highest relapse risk for those after the 6-month treatment was inferred as 66.7% while that of the 12-month treatment was 83.3%. Farmers and those who have high accessibility to MMT services may require additional attention.

Conclusion

It is necessary to implement targeted interventions and education based on the treatment durations of participants to decrease the relapse rate. Meanwhile, those about HIV/sexually transmitted infection prevention and anti-narcotics should be held in the whole process.

Machine learning models for predicting acute kidney injury: a systematic review and critical appraisal

BACKGROUND

The number of studies applying machine learning (ML) to predict acute kidney injury (AKI) has grown steadily over the past decade. We assess and critically appraise the state of the art in ML models for AKI prediction, considering performance, methodological soundness, and applicability.

METHODS

We searched PubMed and ArXiv, extracted data, and critically appraised studies based on the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), and Prediction Model Risk of Bias Assessment Tool (PROBAST) guidelines.

RESULTS

Forty-six studies from 3166 titles were included. Thirty-eight studies developed a model, five developed and externally validated one, and three studies externally validated one. Flexible ML methods were used more often than deep learning, although the latter was common with temporal variables and text as predictors. Predictive performance showed an area under receiver operating curves ranging from 0.49 to 0.99. Our critical appraisal identified a high risk of bias in 39 studies. Some studies lacked internal validation, whereas external validation and interpretability of results were rarely considered. Fifteen studies focused on AKI prediction in the intensive care setting, and the US-derived Medical Information Mart for Intensive Care (MIMIC) data set was commonly used. Reproducibility was limited as data and code were usually unavailable.

CONCLUSIONS

Flexible ML methods are popular for the prediction of AKI, although more complex models based on deep learning are emerging. Our critical appraisal identified a high risk of bias in most models: Studies should use calibration measures and external validation more often, improve model interpretability, and share data and code to improve reproducibility.

Development and Validation of a Personalized Model With Transfer Learning for Acute Kidney Injury Risk Estimation Using Electronic Health Records

IMPORTANCE

Acute kidney injury (AKI) is a heterogeneous syndrome prevalent among hospitalized patients. Personalized risk estimation and risk factor identification may allow effective intervention and improved outcomes.

OBJECTIVE

To develop and validate personalized AKI risk estimation models using electronic health records (EHRs), examine whether personalized models were beneficial in comparison with global and subgroup models, and assess the heterogeneity of risk factors and their outcomes in different subpopulations.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study analyzed EHR data from 1 tertiary care hospital and used machine learning and logistic regression to develop and validate global, subgroup, and personalized risk estimation models. Transfer learning was implemented to enhance the personalized model. Predictor outcomes across subpopulations were analyzed, and metaregression was used to explore predictor interactions. Adults who were hospitalized for 2 or more days from November 1, 2007, to December 31, 2016, were included in the analysis. Patients with moderate or severe kidney dysfunction at admission were excluded. Data were analyzed between August 28, 2019, and May 8, 2022.

EXPOSURES

Clinical and laboratory variables in the EHR.

MAIN OUTCOMES AND MEASURES

The main outcome was AKI of any severity, and AKI was defined using the Kidney Disease: Improving Global Outcomes serum creatinine criteria. Performance of the models was measured with area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and calibration.

RESULTS

The study cohort comprised 76 957 inpatient encounters. Patients had a mean (SD) age of 55.5 (17.4) years and included 42 159 men (54.8%). The personalized model with transfer learning outperformed the global model for AKI estimation in terms of AUROC among general inpatients (0.78 [95% CI, 0.77-0.79] vs 0.76 [95% CI, 0.75-0.76]; P < .001) and across the high-risk subgroups (0.79 [95% CI, 0.78-0.80] vs 0.75 [95% CI, 0.74-0.77]; P < .001) and low-risk subgroups (0.74 [95% CI, 0.73-0.75] vs 0.71 [95% CI, 0.70-0.72]; P < .001). The AUROC improvement reached 0.13 for the high-risk subgroups, such as those undergoing liver transplant and cardiac surgery. Moreover, the personalized model with transfer learning performed better than or comparably with the best published models in well-studied AKI subgroups. Predictor outcomes varied significantly between patients, and interaction analysis uncovered modifiers of the predictor outcomes.

CONCLUSIONS AND RELEVANCE

Results of this study demonstrated that a personalized modeling with transfer learning is an improved AKI risk estimation approach that can be used across diverse patient subgroups. Risk factor heterogeneity and interactions at the individual level highlighted the need for agile, personalized care.

A LASSO-derived clinical score to predict severe acute kidney injury in the cardiac surgery recovery unit: a large retrospective cohort study using the MIMIC database

OBJECTIVES

We aimed to develop an effective tool for predicting severe acute kidney injury (AKI) in patients admitted to the cardiac surgery recovery unit (CSRU).

DESIGN

A retrospective cohort study.

SETTING

Data were extracted from the Medical Information Mart for Intensive Care (MIMIC)-III database, consisting of critically ill participants between 2001 and 2012 in the USA.

PARTICIPANTS

A total of 6271 patients admitted to the CSRU were enrolled from the MIMIC-III database.

PRIMARY AND SECONDARY OUTCOME

Stages 2-3 AKI.

RESULT

As identified by least absolute shrinkage and selection operator (LASSO) and logistic regression, risk factors for AKI included age, sex, weight, respiratory rate, systolic blood pressure, diastolic blood pressure, central venous pressure, urine output, partial pressure of oxygen, sedative use, furosemide use, atrial fibrillation, congestive heart failure and left heart catheterisation, all of which were used to establish a clinical score. The areas under the receiver operating characteristic curve of the model were 0.779 (95% CI: 0.766 to 0.793) for the primary cohort and 0.778 (95% CI: 0.757 to 0.799) for the validation cohort. The calibration curves showed good agreement between the predictions and observations. Decision curve analysis demonstrated that the model could achieve a net benefit.

CONCLUSION

A clinical score built by using LASSO regression and logistic regression to screen multiple clinical risk factors was established to estimate the probability of severe AKI in CSRU patients. This may be an intuitive and practical tool for severe AKI prediction in the CSRU.

An interactive nomogram based on clinical and molecular signatures to predict prognosis in multiple myeloma patients

Although novel drugs and treatments have been developed and improved, multiple myeloma (MM) is still recurrent and difficult to cure. In the present study, the magenta module containing 400 hub genes was determined from the training dataset of GSE24080 through weighted gene co-expression network analysis (WGCNA). Then, using the least absolute shrinkage and selection operator (Lasso) analysis, a fifteen-gene signature was firstly selected and the predictive performance for overall survival (OS) was favorable, which was identified by Receiver Operating Characteristic (ROC) curves. The risk score model was constructed based on survival-associated fifteen genes from the Lasso model, which classified MM patients into high-risk and low-risk groups. Areas under the curve (AUC) of ROC curve and log-rank test showed that the high-risk group was correlated to the dismal survival outcome of MM patients, which was also identified in testing dataset of GSE9782. The calibration plot, the AUC value of the ROC curve and Concordance-index showed that the interactive nomogram with risk score could favorably predict the probability of multi-year OS of MM patients. Therefore, it may help clinicians make a precise therapeutic decision based on the easy-to-use tool of the nomogram.

Super-Enhancer Associated Five-Gene Risk Score Model Predicts Overall Survival in Multiple Myeloma Patients

Multiple myeloma (MM) is a malignant plasma cell tumor with high heterogeneity, characterized by anemia, hypercalcemia, renal failure, and lytic bone lesions. Although various powerful prognostic factors and models have been exploited, the development of more accurate prognosis and treatment for MM patients is still facing many challenges. Given the essential roles of super-enhancer (SE) associated genes in the tumorigenesis of MM, we tried to initially screen and identify the significant prognostic factors from SE associated genes in MM by the least absolute shrinkage and selection operator (Lasso) penalized Cox regression, univariate and multivariate Cox regression analysis using GSE24080 and GSE9782 datasets. Risk score model of five genes including CSGALNACT1, FAM53B, TAPBPL, REPIN1, and DDX11, was further constructed and the Kaplan-Meier (K-M) curves showed that the low-risk group seems to have better clinical outcome of survival compared to the high-risk group. Time-dependent receiver operating characteristic (ROC) curves presented the favorable performance of the model. An interactive nomogram consisting of the five-gene risk group and eleven clinical traits was established and identified by calibration curves. Therefore, the risk score model of SE associated five genes developed here could be used to predict the prognosis of MM patients, which may assist the clinical treatment of MM patients in the future.

Hyponatremia in Patients with Hematologic Diseases

Hyponatremia is the most common electrolyte disorder in clinical practice and is associated with increased morbidity and mortality. It is frequently encountered in hematologic patients with either benign or malignant diseases. Several underlying mechanisms, such as hypovolemia, infections, toxins, renal, endocrine, cardiac, and liver disorders, as well as the use of certain drugs appear to be involved in the development or the persistence of hyponatremia. This review describes the pathophysiology of hyponatremia and discusses thoroughly the contributing factors and mechanisms that may be encountered specifically in patients with hematologic disorders. The involvement of the syndrome of inappropriate antidiuretic hormone (SIADH) secretion and renal salt wasting syndrome (RSWS) in the development of hyponatremia in such patients, as well as their differential diagnosis and management, are also presented. Furthermore, the distinction between true hyponatremia and pseudohyponatremia is explained. Finally, a practical algorithm for the evaluation of hyponatremia in hematologic patients, as well as the principles of hyponatremia management, are included in this review.