Comparing the predictive value of neural network models to logistic regression models on the risk of death for small-cell lung cancer patients

Application of machine learning for lung cancer survival prognostication-A systematic review and meta-analysis

Introduction

Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer.

Methods

We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models.

Results

The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models.

Conclusion

Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.

Assessment of risk based on variant pathways and establishment of an artificial neural network model of thyroid cancer

BACKGROUND

This study aimed to establish an artificial neural network (ANN) model based on variant pathways to predict the risk of thyroid cancer.

METHODS

The RNASeq data of 482 thyroid cancer samples were downloaded from the TCGA database. The samples were divided into low-risk and high-risk groups, followed by identification of differentially expressed genes (DEGs). Co-expression analysis and pathway enrichment analysis were then performed. The variant pathways were screened according to the functional deviation score of each pathway, and an ANN model was established. Finally, the efficiency of the ANN model for risk assessment was validated by survival analysis and analysis of an independent microarray dataset (GSE34289) for thyroid cancer.

RESULTS

In total, 190 DEGs (85 up-regulated and 105 down-regulated) were identified between the low-risk and high-risk groups. Ten risk-related variant pathways were identified between the low-risk and high-risk groups, which were related to inflammatory and immune responses. Based on these variant pathways, an ANN model was built, consisting of an input layer, two hidden layers, and an output layer, corresponding to 15, 8, 5, and 1 neuron, respectively. Survival analysis showed that this model could effectively distinguish the samples with different risks. Analysis of microarray dataset GSE34289 showed that the accuracy of this model for predicating low-risk and high-risk samples was 77.5 and 86.0%, respectively.

CONCLUSIONS

This study suggests that the ANN model based on variant pathways can be used for effectively evaluating the risk of thyroid cancer.

Prediction of Emergency Department Hospital Admission Based on Natural Language Processing and Neural Networks

OBJECTIVE

To describe and compare logistic regression and neural network modeling strategies to predict hospital admission or transfer following initial presentation to Emergency Department (ED) triage with and without the addition of natural language processing elements.

METHODS

Using data from the National Hospital Ambulatory Medical Care Survey (NHAMCS), a cross-sectional probability sample of United States EDs from 2012 and 2013 survey years, we developed several predictive models with the outcome being admission to the hospital or transfer vs. discharge home. We included patient characteristics immediately available after the patient has presented to the ED and undergone a triage process. We used this information to construct logistic regression (LR) and multilayer neural network models (MLNN) which included natural language processing (NLP) and principal component analysis from the patient's reason for visit. Ten-fold cross validation was used to test the predictive capacity of each model and receiver operating curves (AUC) were then calculated for each model.

RESULTS

Of the 47,200 ED visits from 642 hospitals, 6,335 (13.42%) resulted in hospital admission (or transfer). A total of 48 principal components were extracted by NLP from the reason for visit fields, which explained 75% of the overall variance for hospitalization. In the model including only structured variables, the AUC was 0.824 (95% CI 0.818-0.830) for logistic regression and 0.823 (95% CI 0.817-0.829) for MLNN. Models including only free-text information generated AUC of 0.742 (95% CI 0.731- 0.753) for logistic regression and 0.753 (95% CI 0.742-0.764) for MLNN. When both structured variables and free text variables were included, the AUC reached 0.846 (95% CI 0.839-0.853) for logistic regression and 0.844 (95% CI 0.836-0.852) for MLNN.

CONCLUSIONS

The predictive accuracy of hospital admission or transfer for patients who presented to ED triage overall was good, and was improved with the inclusion of free text data from a patient's reason for visit regardless of modeling approach. Natural language processing and neural networks that incorporate patient-reported outcome free text may increase predictive accuracy for hospital admission.

γ -H2AX: A Novel Prognostic Marker in a Prognosis Prediction Model of Patients with Early Operable Non-Small Cell Lung Cancer

Cancer is a leading cause of death worldwide and the prognostic evaluation of cancer patients is of great importance in medical care. The use of artificial neural networks in prediction problems is well established in human medical literature. The aim of the current study was to assess the prognostic value of a series of clinical and molecular variables with the addition of γ -H2AX-a new DNA damage response marker-for the prediction of prognosis in patients with early operable non-small cell lung cancer by comparing the γ -H2AX-based artificial network prediction model with the corresponding LR one. Two prognostic models of 96 patients with 27 input variables were constructed by using the parameter-increasing method in order to compare the predictive accuracy of neural network and logistic regression models. The quality of the models was evaluated by an independent validation data set of 11 patients. Neural networks outperformed logistic regression in predicting the patient's outcome according to the experimental results. To assess the importance of the two factors p53 and γ -H2AX, models without these two variables were also constructed. JR and accuracy of these models were lower than those of the models using all input variables, suggesting that these biological markers are very important for optimal performance of the models. This study indicates that neural networks may represent a potentially more useful decision support tool than conventional statistical methods for predicting the outcome of patients with non-small cell lung cancer and that some molecular markers, such as γ -H2AX, enhance their predictive ability.

Comparing models for quantitative risk assessment: an application to the European Registry of foreign body injuries in children

Risk Assessment is the systematic study of decisions subject to uncertain consequences. An increasing interest has been focused on modeling techniques like Bayesian Networks since their capability of (1) combining in the probabilistic framework different type of evidence including both expert judgments and objective data; (2) overturning previous beliefs in the light of the new information being received and (3) making predictions even with incomplete data. In this work, we proposed a comparison among Bayesian Networks and other classical Quantitative Risk Assessment techniques such as Neural Networks, Classification Trees, Random Forests and Logistic Regression models. Hybrid approaches, combining both Classification Trees and Bayesian Networks, were also considered. Among Bayesian Networks, a clear distinction between purely data-driven approach and combination of expert knowledge with objective data is made. The aim of this paper consists in evaluating among this models which best can be applied, in the framework of Quantitative Risk Assessment, to assess the safety of children who are exposed to the risk of inhalation/insertion/aspiration of consumer products. The issue of preventing injuries in children is of paramount importance, in particular where product design is involved: quantifying the risk associated to product characteristics can be of great usefulness in addressing the product safety design regulation. Data of the European Registry of Foreign Bodies Injuries formed the starting evidence for risk assessment. Results showed that Bayesian Networks appeared to have both the ease of interpretability and accuracy in making prediction, even if simpler models like logistic regression still performed well.

A comparative study on entrepreneurial attitudes modeled with logistic regression and Bayes nets

Entrepreneurship research is receiving increasing attention in our context, as entrepreneurs are key social agents involved in economic development. We compare the success of the dichotomic logistic regression model and the Bayes simple classifier to predict entrepreneurship, after manipulating the percentage of missing data and the level of categorization in predictors. A sample of undergraduate university students (N = 1230) completed five scales (motivation, attitude towards business creation, obstacles, deficiencies, and training needs) and we found that each of them predicted different aspects of the tendency to business creation. Additionally, our results show that the receiver operating characteristic (ROC) curve is affected by the rate of missing data in both techniques, but logistic regression seems to be more vulnerable when faced with missing data, whereas Bayes nets underperform slightly when categorization has been manipulated. Our study sheds light on the potential entrepreneur profile and we propose to use Bayesian networks as an additional alternative to overcome the weaknesses of logistic regression when missing data are present in applied research.

Which is a more accurate predictor in colorectal survival analysis? Nine data mining algorithms vs. the TNM staging system

OBJECTIVE

Over the past decades, many studies have used data mining technology to predict the 5-year survival rate of colorectal cancer, but there have been few reports that compared multiple data mining algorithms to the TNM classification of malignant tumors (TNM) staging system using a dataset in which the training and testing data were from different sources. Here we compared nine data mining algorithms to the TNM staging system for colorectal survival analysis.

METHODS

Two different datasets were used: 1) the National Cancer Institute's Surveillance, Epidemiology, and End Results dataset; and 2) the dataset from a single Chinese institution. An optimization and prediction system based on nine data mining algorithms as well as two variable selection methods was implemented. The TNM staging system was based on the 7(th) edition of the American Joint Committee on Cancer TNM staging system.

RESULTS

When the training and testing data were from the same sources, all algorithms had slight advantages over the TNM staging system in predictive accuracy. When the data were from different sources, only four algorithms (logistic regression, general regression neural network, bayesian networks, and Naïve Bayes) had slight advantages over the TNM staging system. Also, there was no significant differences among all the algorithms (p>0.05).

CONCLUSIONS

The TNM staging system is simple and practical at present, and data mining methods are not accurate enough to replace the TNM staging system for colorectal cancer survival prediction. Furthermore, there were no significant differences in the predictive accuracy of all the algorithms when the data were from different sources. Building a larger dataset that includes more variables may be important for furthering predictive accuracy.

BP Neural Network and Multiple Linear Regression in Acute Hospitalization Costs in the Comparative Study

The BP neural network is the important component of artificial neural networks, and gradually becomes a branch of the computation statistics. With its many characteristics such as large-scale parallel information processing, excellent self-adaptation and self-learning, the BP neural network has been used in solving the complex nonlinear dynamic system prediction. The BP neural network does not need the precise mathematical model, does not have any supposition request to the material itself. Its processing non-linear problem's ability is stronger than traditional statistical methods. By means of contrasting the BP neural network and the multi-dimensional linear regression ,this article discoveries that the BP neural network fitting ability is more stronger, the prediction performance is more stable, may be further applied and promoted in analysis and forecast of the continual material factor.

Informatics in radiology: comparison of logistic regression and artificial neural network models in breast cancer risk estimation

Computer models in medical diagnosis are being developed to help physicians differentiate between healthy patients and patients with disease. These models can aid in successful decision making by allowing calculation of disease likelihood on the basis of known patient characteristics and clinical test results. Two of the most frequently used computer models in clinical risk estimation are logistic regression and an artificial neural network. A study was conducted to review and compare these two models, elucidate the advantages and disadvantages of each, and provide criteria for model selection. The two models were used for estimation of breast cancer risk on the basis of mammographic descriptors and demographic risk factors. Although they demonstrated similar performance, the two models have unique characteristics-strengths as well as limitations-that must be considered and may prove complementary in contributing to improved clinical decision making.

Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases

OBJECTIVES

The aim was to construct and validate algorithms for osteoporosis case ascertainment from administrative databases and to estimate the population prevalence of osteoporosis for these algorithms.

STUDY DESIGN AND SETTING

Artificial neural networks, classification trees, and logistic regression were applied to hospital, physician, and pharmacy data from Manitoba, Canada. Discriminative performance and calibration (i.e., error) were compared for algorithms defined from different sets of diagnosis, prescription drug, comorbidity, and demographic variables. Algorithms were validated against a regional bone mineral density testing program.

RESULTS

Discriminative performance and calibration were poorer and sensitivity was generally lower for algorithms based on diagnosis codes alone than for algorithms based on an expanded set of data features that included osteoporosis prescriptions and age. Validation measures were similar for neural networks and classification trees, but prevalence estimates were lower for the former model.

CONCLUSION

Multiple features of administrative data generally resulted in improved sensitivity of osteoporosis case-detection algorithm without loss of specificity. However, prevalence estimates using an expanded set of features were still slightly lower than estimates from a population-based study with primary data collection. The classification methods developed in this study can be extended to other chronic diseases for which there may be multiple markers in administrative data.

Osteopontin-c is a selective marker of breast cancer

While the acquisition of invasiveness is a critical step in early stage breast carcinomas (DCIS), no established molecular markers reliably identify tumor progression. The metastasis gene osteopontin is subject to alternative splicing, which yields 3 messages, osteopontin-a, osteopontin-b and osteopontin-c. Osteopontin-c is selectively expressed in invasive, but not in noninvasive, breast tumor cell lines, and it effectively supports anchorage independence. We evaluated osteopontin-c as a biomarker. The RNA message for osteopontin-c was present in 16 of 20 breast cancers (80%), but was undetectable in 22 normal specimens obtained from reduction mammoplasty. In contrast, osteopontin-a RNA was expressed at various levels in all 20 breast cancers, 11 tumor-surrounding tissues and 21 normal samples. The splice variant osteopontin-b was present at barely detectable levels in 18 of 20 cancers and in 6 of 22 normal breasts. By immunohistochemistry, 66 of 69 normal breasts were negative, while 3 showed low level staining. Among the breast cancers, 43 of 56 cores (77%) stained positive for osteopontin-c. When correlated with tumor grade, the staining for osteopontin-c increased from grade 1 to grade 3. In a total of 178 breast specimens analyzed, osteopontin-c was present in 78% of cancers, 36% of surrounding tissues and 0% of normal tissues. Furthermore, osteopontin-c detects a higher fraction of breast cancers than estrogen receptor (ER), progesterone receptor or HER2. In conjunction, osteopontin-c, ER and HER2 reliably predict grade 2-3 breast cancer. Hence, osteopontin-c is a diagnostic and prognostic marker that may have value in a diagnostic panel together with conventional breast cancer markers.

Comparison of the levels of accuracy of an artificial neural network model and a logistic regression model for the diagnosis of acute appendicitis

An accurate diagnosis of acute appendicitis in the early stage is often difficult, and decision support tools to improve such a diagnosis might be required. This study compared the levels of accuracy of artificial neural network models and logistic regression models for the diagnosis of acute appendicitis. Data from 169 patients presenting with acute abdomen were used for the analyses. Nine variables were used for the evaluation of the accuracy of the two models. The constructed models were validated by the ".632+ bootstrap method". The levels of accuracy of the two models for diagnosis were compared by error rate and areas under receiver operating characteristic curves. The artificial neural network models provided more accurate results than did the logistic regression models for both indices, especially when categorical variables or normalized variables were used. The most accurate diagnosis was obtained by the artificial neural network model using normalized variables.