Machine learning methods for anticipating the psychological distress in patients with Alzheimer's disease

Identifying the predictors of severe psychological distress by auto-machine learning methods

Social stress in daily life and the COVID-19 pandemic have greatly impacted the mental health of the population. Early detection of a predisposition to severe psychological distress is essential for timely interventions. This paper analyzed 4036 samples participating in the 2019-2020 National Health Information Trends Survey (HINTS) and identified 57 candidate predictors of severe psychological distress based on univariate chi-square and t-test analyses. Five machine learning methods, namely logistic regression (LR), automatic generalized linear models (Auto-GLM), automatic random forests (Auto-Random Forests), automatic deep neural networks (Auto-Deep learning) and automatic gradient boosting machines (Auto-GBM), were employed to model synthetic minority oversampling technique-based (SMOTE) resampled data and identify predictors of severe psychological distress. Predictors were evaluated by odds ratios in logistic models and variable importance in the other models. Forty-seven variables were identified as significant predictors of severe psychological distress, including 13 sociodemographic variables and 34 variables related to individual lifestyle and behavioral habits. Among them, new potentially relevant variables related to an individual's level of concern and trust in cancer information, exposure to health care providers, and cancer screening and awareness are included. The performance of each model was evaluated using five-fold cross-validation. The optimal model performance-wise was Auto-GBM with an accuracy of 89.75%, a precision of 89.68%, a recall of 89.31%, an F1-score of 89.48% and an AUC of 95.57%. Significant predictors of severe psychological distress were identified in this study and the value of machine learning methods in predicting severe psychological distress is demonstrated, thereby enhancing pre-prediction and clinical decision-making of severe psychological distress problems.

Machine Learning Methods to Identify Predictors of Psychological Distress

As people pay ever-increasing attention to the problems caused by psychological stress, research on its influencing factors becomes crucial. This study analyzed the Health Information National Trends Survey (HINTS, Cycle 3 and Cycle 4) data (N = 5484) and assessed the outcomes using descriptive statistics, Chi-squared tests, and t-tests. Four machine learning algorithms were applied for modeling: logistic regression (linear), random forests (RF) (ensemble), the artificial neural network (ANN) (nonlinear), and gradient boosting (GB) (ensemble). The samples were randomly assigned to a 50% training set and a 50% validation set. Twenty-six preselected variables from the databases were used in the study as predictors, and the four models identified twenty predictors of psychological distress. The essence of this paper is a binary classification problem of judging whether an individual has psychological distress based on many different factors. Therefore, accuracy, precision, recall, F1-score, and AUC were used to evaluate the model performance. The logistic regression model selected predictors by forward selection, backward selection, and stepwise regression; variable importance values were used to identify predictors in the other three machine learning methods. Of the four machine learning models, the ANN exhibited the best predictive effect (AUC = 73.90%). A range of predictors of psychological distress was identified by combining the four machine learning models, which would help improve the performance of the existing mental health screening tools.

Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review

Background

Artificial intelligence (AI) holds the promise of supporting nurses’ clinical decision-making in complex care situations or conducting tasks that are remote from direct patient interaction, such as documentation processes. There has been an increase in the research and development of AI applications for nursing care, but there is a persistent lack of an extensive overview covering the evidence base for promising application scenarios.

Objective

This study synthesizes literature on application scenarios for AI in nursing care settings as well as highlights adjacent aspects in the ethical, legal, and social discourse surrounding the application of AI in nursing care.

Methods

Following a rapid review design, PubMed, CINAHL, Association for Computing Machinery Digital Library, Institute of Electrical and Electronics Engineers Xplore, Digital Bibliography & Library Project, and Association for Information Systems Library, as well as the libraries of leading AI conferences, were searched in June 2020. Publications of original quantitative and qualitative research, systematic reviews, discussion papers, and essays on the ethical, legal, and social implications published in English were included. Eligible studies were analyzed on the basis of predetermined selection criteria.

Results

The titles and abstracts of 7016 publications and 704 full texts were screened, and 292 publications were included. Hospitals were the most prominent study setting, followed by independent living at home; fewer application scenarios were identified for nursing homes or home care. Most studies used machine learning algorithms, whereas expert or hybrid systems were entailed in less than every 10th publication. The application context of focusing on image and signal processing with tracking, monitoring, or the classification of activity and health followed by care coordination and communication, as well as fall detection, was the main purpose of AI applications. Few studies have reported the effects of AI applications on clinical or organizational outcomes, lacking particularly in data gathered outside laboratory conditions. In addition to technological requirements, the reporting and inclusion of certain requirements capture more overarching topics, such as data privacy, safety, and technology acceptance. Ethical, legal, and social implications reflect the discourse on technology use in health care but have mostly not been discussed in meaningful and potentially encompassing detail.

Conclusions

The results highlight the potential for the application of AI systems in different nursing care settings. Considering the lack of findings on the effectiveness and application of AI systems in real-world scenarios, future research should reflect on a more nursing care–specific perspective toward objectives, outcomes, and benefits. We identify that, crucially, an advancement in technological-societal discourse that surrounds the ethical and legal implications of AI applications in nursing care is a necessary next step. Further, we outline the need for greater participation among all of the stakeholders involved.

A nonparametric Bayesian method of translating machine learning scores to probabilities in clinical decision support

BACKGROUND

Probabilistic assessments of clinical care are essential for quality care. Yet, machine learning, which supports this care process has been limited to categorical results. To maximize its usefulness, it is important to find novel approaches that calibrate the ML output with a likelihood scale. Current state-of-the-art calibration methods are generally accurate and applicable to many ML models, but improved granularity and accuracy of such methods would increase the information available for clinical decision making. This novel non-parametric Bayesian approach is demonstrated on a variety of data sets, including simulated classifier outputs, biomedical data sets from the University of California, Irvine (UCI) Machine Learning Repository, and a clinical data set built to determine suicide risk from the language of emergency department patients.

RESULTS

The method is first demonstrated on support-vector machine (SVM) models, which generally produce well-behaved, well understood scores. The method produces calibrations that are comparable to the state-of-the-art Bayesian Binning in Quantiles (BBQ) method when the SVM models are able to effectively separate cases and controls. However, as the SVM models' ability to discriminate classes decreases, our approach yields more granular and dynamic calibrated probabilities comparing to the BBQ method. Improvements in granularity and range are even more dramatic when the discrimination between the classes is artificially degraded by replacing the SVM model with an ad hoc k-means classifier.

CONCLUSIONS

The method allows both clinicians and patients to have a more nuanced view of the output of an ML model, allowing better decision making. The method is demonstrated on simulated data, various biomedical data sets and a clinical data set, to which diverse ML methods are applied. Trivially extending the method to (non-ML) clinical scores is also discussed.

Prediction of axillary lymph node metastasis in primary breast cancer patients using a decision tree-based model

Background

The aim of this study was to develop a new data-mining model to predict axillary lymph node (AxLN) metastasis in primary breast cancer. To achieve this, we used a decision tree-based prediction method—the alternating decision tree (ADTree).

Methods

Clinical datasets for primary breast cancer patients who underwent sentinel lymph node biopsy or AxLN dissection without prior treatment were collected from three institutes (institute A, n = 148; institute B, n = 143; institute C, n = 174) and were used for variable selection, model training and external validation, respectively. The models were evaluated using area under the receiver operating characteristics (ROC) curve analysis to discriminate node-positive patients from node-negative patients.

Results

The ADTree model selected 15 of 24 clinicopathological variables in the variable selection dataset. The resulting area under the ROC curve values were 0.770 [95% confidence interval (CI), 0.689–0.850] for the model training dataset and 0.772 (95% CI: 0.689–0.856) for the validation dataset, demonstrating high accuracy and generalization ability of the model. The bootstrap value of the validation dataset was 0.768 (95% CI: 0.763–0.774).

Conclusions

Our prediction model showed high accuracy for predicting nodal metastasis in patients with breast cancer using commonly recorded clinical variables. Therefore, our model might help oncologists in the decision-making process for primary breast cancer patients before starting treatment.