Non-obvious correlations to disease management unraveled by Bayesian artificial intelligence analyses of CMS data

Identification and validation of N-acetylputrescine in combination with non-canonical clinical features as a Parkinson's disease biomarker panel

Parkinson's disease is a progressive neurodegenerative disorder in which loss of dopaminergic neurons in the substantia nigra results in a clinically heterogeneous group with variable motor and non-motor symptoms with a degree of misdiagnosis. Only 3-25% of sporadic Parkinson's patients present with genetic abnormalities that could represent a risk factor, thus environmental, metabolic, and other unknown causes contribute to the pathogenesis of Parkinson's disease, which highlights the critical need for biomarkers. In the present study, we prospectively collected and analyzed plasma samples from 194 Parkinson's disease patients and 197 age-matched non-diseased controls. N-acetyl putrescine (NAP) in combination with sense of smell (B-SIT), depression/anxiety (HADS), and acting out dreams (RBD1Q) clinical measurements demonstrated combined diagnostic utility. NAP was increased by 28% in Parkinsons disease patients and exhibited an AUC of 0.72 as well as an OR of 4.79. The clinical and NAP panel demonstrated an area under the curve, AUC = 0.9 and an OR of 20.4. The assessed diagnostic panel demonstrates combinatorial utility in diagnosing Parkinson's disease, allowing for an integrated interpretation of disease pathophysiology and highlighting the use of multi-tiered panels in neurological disease diagnosis.

Research and Implementation of Mobile Internet Management Optimization and Intelligent Information System Based on Smart Decision

The way by which artificial intelligence is implemented is similar to the thinking process of the human brain. People obtain information about external conditions through five senses, namely, vision, hearing, smell, taste, and touch, and, through the further processing of the brain, it forms meaningful decision-making elements. Then, through the process of analysis and reasoning, further decisions are made. In the information age, the application of intelligent management information systems in various fields has promoted the modernization and intelligence of social development. From the perspective of intelligent decision-making, this paper analyzes the requirements of intelligent information systems and designs an intelligent information system based on mobile Internet management optimization, including system management optimization, and proposes an environment-based layer, network transport layer, and the three-tier system architecture of the smart service application layer. Finally, this paper considers the problem of data fusion after system expansion. According to the existing fuzzy fusion algorithm, a weight-based fuzzy fusion algorithm is proposed. The simulation analysis shows that the algorithm can be effectively applied in intelligent information systems.

A comprehensive scoping review of Bayesian networks in healthcare: Past, present and future

No comprehensive review of Bayesian networks (BNs) in healthcare has been published in the past, making it difficult to organize the research contributions in the present and identify challenges and neglected areas that need to be addressed in the future. This unique and novel scoping review of BNs in healthcare provides an analytical framework for comprehensively characterizing the domain and its current state. A literature search of health and health informatics literature databases using relevant keywords found 3810 articles that were reduced to 123. This was after screening out those presenting Bayesian statistics, meta-analysis or neural networks, as opposed to BNs and those describing the predictive performance of multiple machine learning algorithms, of which BNs were simply one type. Using the novel analytical framework, we show that: (1) BNs in healthcare are not used to their full potential; (2) a generic BN development process is lacking; (3) limitations exist in the way BNs in healthcare are presented in the literature, which impacts understanding, consensus towards systematic methodologies, practice and adoption; and (4) a gap exists between having an accurate BN and a useful BN that impacts clinical practice. This review highlights several neglected issues, such as restricted aims of BNs, ad hoc BN development methods, and the lack of BN adoption in practice and reveals to researchers and clinicians the need to address these problems. To map the way forward, the paper proposes future research directions and makes recommendations regarding BN development methods and adoption in practice.

Bayesian networks in healthcare: What is preventing their adoption?

There has been much research effort expended toward the use of Bayesian networks (BNs) in medical decision-making. However, because of the gap between developing an accurate BN and demonstrating its clinical usefulness, this has not resulted in any widespread BN adoption in clinical practice. This paper investigates this problem with the aim of finding an explanation and ways to address the problem through a comprehensive literature review of articles describing BNs in healthcare. Based on the literature collection that has been systematically narrowed down from 3810 to 116 most relevant articles, this paper analyses the benefits, barriers and facilitating factors (BBF) for implementing BN-based systems in healthcare using the ITPOSMO-BBF framework. A key finding is that works in the literature rarely consider barriers and even when these were identified they were not connected to facilitating factors. The main finding is that the barriers can be grouped into: (1) data inadequacies; (2) clinicians' resistance to new technologies; (3) lack of clinical credibility; (4) failure to demonstrate clinical impact; (5) absence of an acceptable predictive performance; and (6) absence of evidence for model's generalisability. The facilitating factors can be grouped into: (1) data collection improvements; (2) software and technological improvements; (3) having interpretable and easy to use BN-based systems; (4) clinical involvement in the development or review of the model; (5) investigation of model's clinical impact; (6) internal validation of the model's performance; and (7) external validation of the model. These groupings form a strong basis for a generic framework that could be used for formulating strategies for ensuring BN-based clinical decision-support system adoption in frontline care settings. The output of this review is expected to enhance the dialogue among researchers by providing a deeper understanding for the neglected issue of BN adoption in practice and promoting efforts for implementing BN-based systems.

Bayesian Model Infers Drug Repurposing Candidates for Treatment of COVID-19

The emergence of COVID-19 progressed into a global pandemic that has functionally put the world at a standstill and catapulted major healthcare systems into an overburdened state. The dire need for therapeutic strategies to mitigate and successfully treat COVID-19 is now a public health crisis with national security implications for many countries. The current study employed Bayesian networks to a longitudinal proteomic dataset generated from Caco-2 cells transfected with SARS-CoV-2 (isolated from patients returning from Wuhan to Frankfurt). Two different approaches were employed to assess the Bayesian models, a titer-center topology analysis and a drug signature enrichment analysis. Topology analysis identified a set of proteins directly linked to the SAR-CoV2 titer, including ACE2, a SARS-CoV-2 binding receptor, MAOB and CHECK1. Aligning with the topology analysis, MAOB and CHECK1 were also identified within the enriched drug-signatures. Taken together, the data output from this network has identified nodal host proteins that may be connected to 18 chemical compounds, some already marketed, which provides an immediate opportunity to rapidly triage these assets for safety and efficacy against COVID-19.

Development of prognostic model for patients at CKD stage 3a and 3b in South Central China using computational intelligence

BACKGROUND

Chronic kidney disease (CKD) stage 3 was divided into two subgroups by eGFR (45 mL/ min 1.73 m²). There is difference in prevalence of CKD, racial differences, economic development, genetic, and environmental backgrounds between China and Western countries.

METHODS

We used a computational intelligence model (CKD stage 3 Modeling, CSM) to distinguish CKD stage 3 with CKD stage 3a/3b by data distribution rules, pearson correlation coefficient (PCC), spearman correlation (SCC) analysis, logistic regression (LR), random forest (RF), support vector machine (SVM), and neural network (Nnet) to develop Prognostic Model for patients with CKD stage 3a/3b in South Central China. Furthermore, we used RF to discover risk factors of progression of CKD stage 3a and 3b to CKD stage 5. 1090 cases of CKD stage 3 patients in Xiangya Hospital were collected. Among them, 455 patients progressed to CKD stage 5 in a median follow-up of 4 years (IQR 4.295, 4.489).

RESULTS

We found that the common risk factors for progression of CKD stage 3a/3b to CKD stage 5 included albumin, creatinine, total protein, etc. Proteinuria, direct bilirubin, hemoglobin, etc. accounted for the progression from stage CKD stage 3a to stage 5. The risk factors for CKD stage 3b progression to stage 5 included low-density lipoprotein cholesterol, diabetes, eosinophil percentage, etc. CONCLUSIONS: CSM could be used as a point-of-care test to screen patients at high risk for disease progression, might allowing individualized therapeutic management.

Multi-omic serum biomarkers for prognosis of disease progression in prostate cancer

Background

Predicting the clinical course of prostate cancer is challenging due to the wide biological spectrum of the disease. The objective of our study was to identify prostate cancer prognostic markers in patients ‘sera using a multi-omics discovery platform.

Methods

Pre-surgical serum samples collected from a longitudinal, racially diverse, prostate cancer patient cohort (N = 382) were examined. Linear Regression and Bayesian computational approaches integrated with multi-omics, were used to select markers to predict biochemical recurrence (BCR). BCR-free survival was modeled using unadjusted Kaplan–Meier estimation curves and multivariable Cox proportional hazards analysis, adjusted for key pathologic variables. Receiver operating characteristic (ROC) curve statistics were used to examine the predictive value of markers in discriminating BCR events from non-events. The findings were further validated by creating a training set (N = 267) and testing set (N = 115) from the cohort.

Results

Among 382 patients, 72 (19%) experienced a BCR event in a median follow-up time of 6.9 years. Two proteins—Tenascin C (TNC) and Apolipoprotein A1V (Apo-AIV), one metabolite—1-Methyladenosine (1-MA) and one phospholipid molecular species phosphatidic acid (PA) 18:0-22:0 showed a cumulative predictive performance of AUC = 0.78 [OR (95% CI) = 6.56 (2.98–14.40), P < 0.05], in differentiating patients with and without BCR event. In the validation set all four metabolites consistently reproduced an equivalent performance with high negative predictive value (NPV; > 80%) for BCR. The combination of pTstage and Gleason score with the analytes, further increased the sensitivity [AUC = 0.89, 95% (CI) = 4.45–32.05, P < 0.05], with an increased NPV (0.96) and OR (12.4) for BCR. The panel of markers combined with the pathological parameters demonstrated a more accurate prediction of BCR than the pathological parameters alone in prostate cancer.

Conclusions

In this study, a panel of serum analytes were identified that complemented pathologic patient features in predicting prostate cancer progression. This panel offers a new opportunity to complement current prognostic markers and to monitor the potential impact of primary treatment versus surveillance on patient oncological outcome.

A Data-Driven Approach to Predicting Septic Shock in the Intensive Care Unit

Early diagnosis of sepsis and septic shock has been unambiguously linked to lower mortality and better patient outcomes. Despite this, there is a strong unmet need for a reliable clinical tool that can be used for large-scale automated screening to identify high-risk patients. We addressed the following questions: Can a novel algorithm to identify patients at high risk of septic shock 24 hours before diagnosis be discovered using available clinical data? What are performance characteristics of this predictive algorithm? Can current metrics for evaluation of sepsis be improved using novel algorithm? Publicly available data from the intensive care unit setting was used to build septic shock and control patient cohorts. Using Bayesian networks, causal relationships between diagnosis groups, procedure groups, laboratory results, and demographic data were inferred. Predictive model for septic shock 24 hours prior to digital diagnosis was built based on inferred causal networks. Sepsis risk scores were augmented by de novo inferred model and performance was evaluated. A novel predictive model to identify high-risk patients 24 hours ahead of time, with area under curve of 0.81, negative predictive value of 0.87, and a positive predictive value as high as 0.65 was built. The specificity of quick sequential organ failure assessment, systemic inflammatory response syndrome, and modified early warning score was improved when augmented with the novel model, whereas no improvements were made to the sequential organ failure assessment score. We used a data-driven, expert knowledge agnostic method to build a screening algorithm for early detection of septic shock. The model demonstrates strong performance in the data set used and provides a basis for expanding this work toward building an algorithm that is used to screen patients based on electronic medical record data in real time.

Applying a Series and Parallel Model and a Bayesian Networks Model to Produce Disaster Chain Susceptibility Maps in the Changbai Mountain area, China

The aim of this project was to produce an earthquake–landslide debris flow disaster chain susceptibility map for the Changbai Mountain region, China, by applying data-driven model series and parallel model and Bayesian Networks model. The accuracy of these two models was then compared. Parameters related to the occurrence of landslide and debris flow disasters, including earthquake intensity, rainfall, elevation, slope, slope aspect, lithology, distance to rivers, distance to faults, land use, and the normalized difference vegetation index (NDVI), were chosen and applied in these two models. Disaster chain susceptibility zones created using the two models were then contrasted and verified using the occurrence of past disasters obtained from remote sensing interpretations and field investigations. Both disaster chain susceptibility maps showed that the high susceptibility zones are situated within a 10 km radius around the Tianchi volcano, whereas the northern and southwestern sections of the study area comprise primarily very low or low susceptibility zones. The two models produced similar and compatible results as indicated by the outcomes of basic linear correlation and cross-correlation analyses. The verification results of the ROC curves were found to be 0.7727 and 0.8062 for the series and parallel model and BN model, respectively. These results indicate that the two models can be used as a preliminary base for further research activities aimed at providing hazard management tools, forecasting services, and early warning systems.