Improving the accuracy of medical diagnosis with causal machine learning

Exploiting biochemical data to improve osteosarcoma diagnosis with deep learning

Early and accurate diagnosis of osteosarcomas (OS) is of great clinical significance, and machine learning (ML) based methods are increasingly adopted. However, current ML-based methods for osteosarcoma diagnosis consider only X-ray images, usually fail to generalize to new cases, and lack explainability. In this paper, we seek to explore the capability of deep learning models in diagnosing primary OS, with higher accuracy, explainability, and generality. Concretely, we analyze the added value of integrating the biochemical data, i.e., alkaline phosphatase (ALP) and lactate dehydrogenase (LDH), and design a model that incorporates the numerical features of ALP and LDH and the visual features of X-ray imaging through a late fusion approach in the feature space. We evaluate this model on real-world clinic data with 848 patients aged from 4 to 81. The experimental results reveal the effectiveness of incorporating ALP and LDH simultaneously in a late fusion approach, with the accuracy of the considered 2608 cases increased to 97.17%, compared to 94.35% in the baseline. Grad-CAM visualizations consistent with orthopedic specialists further justified the model's explainability.

Automatic detection and visualization of temporomandibular joint effusion with deep neural network

This study investigated the usefulness of deep learning-based automatic detection of temporomandibular joint (TMJ) effusion using magnetic resonance imaging (MRI) in patients with temporomandibular disorder and whether the diagnostic accuracy of the model improved when patients' clinical information was provided in addition to MRI images. The sagittal MR images of 2948 TMJs were collected from 1017 women and 457 men (mean age 37.19 ± 18.64 years). The TMJ effusion diagnostic performances of three convolutional neural networks (scratch, fine-tuning, and freeze schemes) were compared with those of human experts based on areas under the curve (AUCs) and diagnosis accuracies. The fine-tuning model with proton density (PD) images showed acceptable prediction performance (AUC = 0.7895), and the from-scratch (0.6193) and freeze (0.6149) models showed lower performances (p < 0.05). The fine-tuning model had excellent specificity compared to the human experts (87.25% vs. 58.17%). However, the human experts were superior in sensitivity (80.00% vs. 57.43%) (all p < 0.001). In gradient-weighted class activation mapping (Grad-CAM) visualizations, the fine-tuning scheme focused more on effusion than on other structures of the TMJ, and the sparsity was higher than that of the from-scratch scheme (82.40% vs. 49.83%, p < 0.05). The Grad-CAM visualizations agreed with the model learned through important features in the TMJ area, particularly around the articular disc. Two fine-tuning models on PD and T2-weighted images showed that the diagnostic performance did not improve compared with using PD alone (p < 0.05). Diverse AUCs were observed across each group when the patients were divided according to age (0.7083-0.8375) and sex (male:0.7576, female:0.7083). The prediction accuracy of the ensemble model was higher than that of the human experts when all the data were used (74.21% vs. 67.71%, p < 0.05). A deep neural network (DNN) was developed to process multimodal data, including MRI and patient clinical data. Analysis of four age groups with the DNN model showed that the 41-60 age group had the best performance (AUC = 0.8258). The fine-tuning model and DNN were optimal for judging TMJ effusion and may be used to prevent true negative cases and aid in human diagnostic performance. Assistive automated diagnostic methods have the potential to increase clinicians' diagnostic accuracy.

Interpretable Causal System Optimization Framework for the Advancement of Biological Effect Prediction and Redesign of Nanoparticles

Nanomedicine has promising applications in disease treatment, given the remarkable safety concerns (e.g., nanotoxicity and inflammation) of nanomaterials, and realizing the trade-off between the immune response and organ burden of NPs and deeply understanding the interactions of the organism-nano systems are crucial to facilitate the biological applications of NPs. Here, we propose an interpretable causal system optimization (ICSO) framework and construct the upstream and downstream tasks of accurate prediction and intelligent NP optimization. ICSO framework screens the key drivers (recovery duration, specific surface area, and nanomaterial size) and potential causal information for immune responses and organ burden, revealing the hidden priming/constraint effects in bionano interactions. ICSO can be used to quantify the thresholds of biological responses to multiple properties (e.g., the specific surface area, diameter, and zeta potential). ICSO provides quantitative information and constraint conditions for the design of highly biocompatible and targeted organ delivery nanomaterials. For example, negative inflammation is reduced by 36.19%, and positive lung accumulation is promoted by 40.14% by optimizing the specific surface areas and shape and increasing the diameter-to-length ratio. ICSO overcomes the limitations of experience-dependent approaches and provides powerful and automated solutions for decision-makers during nanomaterial design.

Development and validation of a Multi-Causal investigation and discovery framework for knowledge harmonization (MINDMerge): A case study with acute kidney injury risk factor discovery using electronic medical records

OBJECTIVE

Accurate diagnoses and personalized treatments in medicine rely on identifying causality. However, existing causal discovery algorithms often yield inconsistent results due to distinct learning mechanisms. To address this challenge, we introduce MINDMerge, a multi-causal investigation and discovery framework designed to synthesize causal graphs from various algorithms.

METHODS

MINDMerge integrates five causal models to reconcile inconsistencies arising from different algorithms. Employing credibility weighting and a novel cycle-breaking mechanism in causal networks, we initially developed and tested MINDMerge using three synthetic networks. Subsequently, we validated its effectiveness in discovering risk factors and predicting acute kidney injury (AKI) using two electronic medical records (EMR) datasets, eICU Collaborative Research Database and MIMIC-III Database. Causal reasoning was employed to analyze the relationships between risk factors and AKI. The identified causal risk factors of AKI were used in building a prediction model, and the prediction model was evaluated using the area under the receiver operating characteristics curve (AUC) and recall.

RESULTS

Synthetic data experiments demonstrated that our model outperformed significantly in capturing ground-truth network structure compared to other causal models. Application of MINDMerge on real-world data revealed direct connections of pulmonary disease, hypertension, diabetes, x-ray assessment, and BUN with AKI. With the identified variables, AKI risk can be inferred at the individual level based on established BNs and prior information. Compared against existing benchmark models, MINDMerge maintained a higher AUC for AKI prediction in both internal (AUC: 0.832) and external network validations (AUC: 0.861).

CONCLUSION

MINDMerge can identify causal risk factors of AKI, serving as a valuable diagnostic tool for clinical decision-making and facilitating effective intervention.

Navigating the future: machine learning's role in revolutionizing antimicrobial stewardship and infection prevention and control

PURPOSE OF REVIEW

This review examines the current state and future prospects of machine learning (ML) in infection prevention and control (IPC) and antimicrobial stewardship (ASP), highlighting its potential to transform healthcare practices by enhancing the precision, efficiency, and effectiveness of interventions against infections and antimicrobial resistance.

RECENT FINDINGS

ML has shown promise in improving surveillance and detection of infections, predicting infection risk, and optimizing antimicrobial use through the development of predictive analytics, natural language processing, and personalized medicine approaches. However, challenges remain, including issues related to data quality, model interpretability, ethical considerations, and integration into clinical workflows.

SUMMARY

Despite these challenges, the future of ML in IPC and ASP is promising, with interdisciplinary collaboration identified as a key factor in overcoming existing barriers. ML's role in advancing personalized medicine, real-time disease monitoring, and effective IPC and ASP strategies signifies a pivotal shift towards safer, more efficient healthcare environments and improved patient care in the face of global antimicrobial resistance challenges.

Machine learning to predict the early recurrence of intrahepatic cholangiocarcinoma: A systematic review and meta‑analysis

The prediction of early recurrent of intrahepatic cholangiocarcinoma (ICC) has been widely investigated; however, the predictive value is currently insufficient. To determine the effectiveness of machine learning (ML) for the diagnosis of early recurrent intrahepatic cholangiocarcinoma (ICC), particularly in comparison with clinical models, the present study aimed to determine which ML model had the best diagnostic performance for inpatients with recurrent ICC. In order to search for studies which could be included, three electronic databases were screened from inception to November 2023. A pairwise meta-analysis was performed to evaluate the diagnostic accuracy of the random effects model. A network meta-analysis was performed to identify the most effective ML-based diagnostic model based on the surface under the cumulative ranking curve score. A total of 5 studies of acceptable quality containing 1,247 patients with ICC were included in the present study. Following pairwise meta-analysis, it was found that the ML-based diagnostic accuracy was greater than that of clinical models (surface under the cumulative ranking curve score closer to 1, with significant differences), which initially proved that the ML-based diagnostic power was more optimal than that of clinical models. According to the network meta-analysis, the nomogram performed the best, indicating that this ML model achieved the best diagnostic accuracy for patients with recurrent ICC. In conclusion, the application of ML-based diagnostic models for patients with recurrent ICC was more optimal than the application of the clinical model. The nomogram model ranked first among the models and is therefore recommended for patients with recurrent ICC.

Machine learning/artificial intelligence in sports medicine: state of the art and future directions

Machine learning (ML) is changing the way health care is practiced and recent applications of these novel statistical techniques have started to impact orthopaedic sports medicine. Machine learning enables the analysis of large volumes of data to establish complex relationships between "input" and "output" variables. These relationships may be more complex than could be established through traditional statistical analysis and can lead to the ability to predict the "output" with high levels of accuracy. Supervised learning is the most common ML approach for healthcare data and recent studies have developed algorithms to predict patient-specific outcome after surgical procedures such as hip arthroscopy and anterior cruciate ligament reconstruction. Deep learning is a higher-level ML approach that facilitates the processing and interpretation of complex datasets through artificial neural networks that are inspired by the way the human brain processes information. In orthopaedic sports medicine, deep learning has primarily been used for automatic image (computer vision) and text (natural language processing) interpretation. While applications in orthopaedic sports medicine have been increasing exponentially, one significant barrier to widespread adoption of ML remains clinician unfamiliarity with the associated methods and concepts. The goal of this review is to introduce these concepts, review current machine learning models in orthopaedic sport medicine, and discuss future opportunities for innovation within the specialty.

Dynamic memristor for physical reservoir computing

Reservoir computing (RC) has attracted considerable attention for its efficient handling of temporal signals and lower training costs. As a nonlinear dynamic system, RC can map low-dimensional inputs into high-dimensional spaces and implement classification using a simple linear readout layer. The memristor exhibits complex dynamic characteristics due to its internal physical processes, which renders them an ideal choice for the implementation of physical reservoir computing (PRC) systems. This review focuses on PRC systems based on memristors, explaining the resistive switching mechanism at the device level and emphasizing the tunability of their dynamic behavior. The development of memristor-based reservoir computing systems is highlighted, along with discussions on the challenges faced by this field and potential future research directions.

A deep neural network-based approach for seizure activity recognition of epilepsy sufferers

Epilepsy is one of the most frequent neurological illnesses caused by epileptic seizures and the second most prevalent neurological ailment after stroke, affecting millions of people worldwide. People with epileptic disease are considered a category of people with disabilities. It significantly impairs a person's capacity to perform daily tasks, especially those requiring focusing or remembering. Electroencephalogram (EEG) signals are commonly used to diagnose people with epilepsy. However, it is tedious, time-consuming, and subjected to human errors. Several machine learning techniques have been applied to recognize epilepsy previously, but they have some limitations. This study proposes a deep neural network (DNN) machine learning model to determine the existing limitations of previous studies by improving the recognition efficiency of epileptic disease. A public dataset is used in this study and classified into training and testing sets. Experiments were performed to evaluate the DNN model with different dataset classification ratios (80:20), (70:30), (60:40), and (50:50) for training and testing, respectively. Results were evaluated by using different performance metrics including validations, and comparison processes that allow the assessment of the model's effectiveness. The experimental results showed that the overall efficiency of the proposed model is the highest compared with previous works, with an accuracy rate of 97%. Thus, this study is more accurate and efficient than the existing seizure detection approaches. DNN model has great potential for recognizing epileptic patient activity using a numerical EEG dataset offering a data-driven approach to improve the accuracy and reliability of seizure detection systems for the betterment of patient care and management of epilepsy.

Multivariate pattern analysis of medical imaging-based Alzheimer's disease

Alzheimer's disease (AD) is a devastating brain disorder that steadily worsens over time. It is marked by a relentless decline in memory and cognitive abilities. As the disease progresses, it leads to a significant loss of mental function. Early detection of AD is essential to starting treatments that can mitigate the progression of this disease and enhance patients' quality of life. This study aims to observe AD's brain functional connectivity pattern to extract essential patterns through multivariate pattern analysis (MVPA) and analyze activity patterns across multiple brain voxels. The optimized feature extraction techniques are used to obtain the important features for performing the training on the models using several hybrid machine learning classifiers for performing binary classification and multi-class classification. The proposed approach using hybrid machine learning classification has been applied to two public datasets named the Open Access Series of Imaging Studies (OASIS) and the AD Neuroimaging Initiative (ADNI). The results are evaluated using performance metrics, and comparisons have been made to differentiate between different stages of AD using visualization tools.

Enhancing Type 2 Diabetes Treatment Decisions With Interpretable Machine Learning Models for Predicting Hemoglobin A1c Changes: Machine Learning Model Development

BACKGROUND

Type 2 diabetes (T2D) is a significant global health challenge. Physicians need to assess whether future glycemic control will be poor on the current trajectory of usual care and usual-care treatment intensifications so that they can consider taking extra treatment measures to prevent poor outcomes. Predicting poor glycemic control from trends in hemoglobin A1c (HbA1c) levels is difficult due to the influence of seasonal fluctuations and other factors.

OBJECTIVE

We sought to develop a model that accurately predicts poor glycemic control among patients with T2D receiving usual care.

METHODS

Our machine learning model predicts poor glycemic control (HbA1c≥8%) using the transformer architecture, incorporating an attention mechanism to process irregularly spaced HbA1c time series and quantify temporal relationships of past HbA1c levels at each time point. We assessed the model using HbA1c levels from 7787 patients with T2D seeing specialist physicians at the University of Tokyo Hospital. The training data include instances of poor glycemic control occurring during usual care with usual-care treatment intensifications. We compared prediction accuracy, assessed with the area under the receiver operating characteristic curve, the area under the precision-recall curve, and the accuracy rate, to that of LightGBM.

RESULTS

The area under the receiver operating characteristic curve, the area under the precision-recall curve, and the accuracy rate (95% confidence limits) of the proposed model were 0.925 (95% CI 0.923-0.928), 0.864 (95% CI 0.852-0.875), and 0.864 (95% CI 0.86-0.869), respectively. The proposed model achieved high prediction accuracy comparable to or surpassing LightGBM's performance. The model prioritized the most recent HbA1c levels for predictions. Older HbA1c levels in patients with poor glycemic control were slightly more influential in predictions compared to patients with good glycemic control.

CONCLUSIONS

The proposed model accurately predicts poor glycemic control for patients with T2D receiving usual care, including patients receiving usual-care treatment intensifications, allowing physicians to identify cases warranting extraordinary treatment intensifications. If used by a nonspecialist, the model's indication of likely future poor glycemic control may warrant a referral to a specialist. Future efforts could incorporate diverse and large-scale clinical data for improved accuracy.

Artificial intelligence and machine learning in axial spondyloarthritis

PURPOSE OF REVIEW

To evaluate the current applications and prospects of artificial intelligence and machine learning in diagnosing and managing axial spondyloarthritis (axSpA), focusing on their role in medical imaging, predictive modelling, and patient monitoring.

RECENT FINDINGS

Artificial intelligence, particularly deep learning, is showing promise in diagnosing axSpA assisting with X-ray, computed tomography (CT) and MRI analyses, with some models matching or outperforming radiologists in detecting sacroiliitis and markers. Moreover, it is increasingly being used in predictive modelling of disease progression and personalized treatment, and could aid risk assessment, treatment response and clinical subtype identification. Variable study designs, sample sizes and the predominance of retrospective, single-centre studies still limit the generalizability of results.

SUMMARY

Artificial intelligence technologies have significant potential to advance the diagnosis and treatment of axSpA, providing more accurate, efficient and personalized healthcare solutions. However, their integration into clinical practice requires rigorous validation, ethical and legal considerations, and comprehensive training for healthcare professionals. Future advances in artificial intelligence could complement clinical expertise and improve patient care through improved diagnostic accuracy and tailored therapeutic strategies, but the challenge remains to ensure that these technologies are validated in prospective multicentre trials and ethically integrated into patient care.

Deep causal learning for pancreatic cancer segmentation in CT sequences

Segmenting the irregular pancreas and inconspicuous tumor simultaneously is an essential but challenging step in diagnosing pancreatic cancer. Current deep-learning (DL) methods usually segment the pancreas or tumor independently using mixed image features, which are disrupted by surrounding complex and low-contrast background tissues. Here, we proposed a deep causal learning framework named CausegNet for pancreas and tumor co-segmentation in 3D CT sequences. Specifically, a causality-aware module and a counterfactual loss are employed to enhance the DL network's comprehension of the anatomical causal relationship between the foreground elements (pancreas and tumor) and the background. By integrating causality into CausegNet, the network focuses solely on extracting intrinsic foreground causal features while effectively learning the potential causality between the pancreas and the tumor. Then based on the extracted causal features, CausegNet applies a counterfactual inference to significantly reduce the background interference and sequentially search for pancreas and tumor from the foreground. Consequently, our approach can handle deformable pancreas and obscure tumors, resulting in superior co-segmentation performance in both public and real clinical datasets, achieving the highest pancreas/tumor Dice coefficients of 86.67%/84.28%. The visualized features and anti-noise experiments further demonstrate the causal interpretability and stability of our method. Furthermore, our approach improves the accuracy and sensitivity of downstream pancreatic cancer risk assessment task by 12.50% and 50.00%, respectively, compared to experienced clinicians, indicating promising clinical applications.

Diagnostic capabilities of ChatGPT in ophthalmology

PURPOSE

The purpose of this study is to assess the diagnostic accuracy of ChatGPT in the field of ophthalmology.

METHODS

This is a retrospective cohort study conducted in one academic tertiary medical center. We reviewed data of patients admitted to the ophthalmology department from 06/2022 to 01/2023. We then created two clinical cases for each patient. The first case is according to the medical history alone (Hx). The second case includes an addition of the clinical examination (Hx and Ex). For each case, we asked for the three most likely diagnoses from ChatGPT, residents, and attendings. Then, we compared the accuracy rates (at least one correct diagnosis) of all groups. Additionally, we evaluated the total duration for completing the assignment between the groups.

RESULTS

ChatGPT, residents, and attendings evaluated 126 cases from 63 patients (history only or history and exam findings for each patient). ChatGPT achieved a significantly lower accurate diagnosis rate (54%) in the Hx, as compared to the residents (75%; p < 0.01) and attendings (71%; p < 0.01). After adding the clinical examination findings, the diagnosis rate of ChatGPT was 68%, whereas for the residents and the attendings, it increased to 94% (p < 0.01) and 86% (p < 0.01), respectively. ChatGPT was 4 to 5 times faster than the attendings and residents.

CONCLUSIONS AND RELEVANCE

ChatGPT showed low diagnostic rates in ophthalmology cases compared to residents and attendings based on patient history alone or with additional clinical examination findings. However, ChatGPT completed the task faster than the physicians.

FPR1, as a Potential Biomarker of Diagnosis and Infliximab Therapy Responses for Crohn's Disease, is Related to Disease Activity, Inflammation and Macrophage Polarization

Purpose

Crohn's disease (CD) represents a multifaceted inflammatory gastrointestinal condition, with a profound significance placed on unraveling its molecular pathways to enhance both diagnostic capabilities and therapeutic interventions. This study focused on identifying a robust macrophage-related signatures (MacroSig) for diagnosing CD, emphasizing the role of FPR1 in macrophage polarization and its implications in CD.

Patients and Methods

Expression profiles from intestinal biopsies and macrophages of 1804 CD patients were retrieved from the Gene Expression Omnibus (GEO). Utilizing CIBERSORTx, differential expression analysis, and weighted correlation network analysis to to identify macrophage-related genes (MRGs). By unsupervised clustering, distinct clusters of CD were identified. Potential biomarkers were identified via using four machine learning algorithms, leading to the establishment of MacroSig which combines insights from 12 machine learning algorithms. Furthermore, the expression of FPR1 was verified in intestinal biopsies of CD patients and two murine experimental colitis models. Finally, we further explored the role of FPR1 in macrophage polarization through single-cell analysis as well as through the study of RAW264.7 cells and peritoneal macrophages.

Results

Two distinct clusters with differential levels of macrophage infiltration and inflammation were identified. The MacroSig, which included FPR1 and LILRB2, exhibited high diagnostic accuracy and outperformed existing biomarkers and signatures. Clinical analysis demonstrated a strong correlation of FPR1 with disease activity, endoscopic inflammation status, and response to infliximab treatment. The expression levels of FPR1 were validated in our CD cohort by immunohistochemistry and confirmed in two colitis mouse models. Single-cell analysis indicated that FPR1 is predominantly expressed in macrophages and monocytes. In vitro studies demonstrated that FPR1 was upregulated in M1 macrophages, and its activation promoted M1 polarization.

Conclusion

We developed a promising diagnostic signature for CD, and targeting FPR1 to modulate macrophage polarization may represent a novel therapeutic strategy.

Exploratory analysis using machine learning algorithms to predict pinch strength by anthropometric and socio-demographic features

Objectives. This study examines the role of different machine learning (ML) algorithms to determine which socio-demographic factors and hand-forearm anthropometric dimensions can be used to accurately predict hand function. Methods. The cross-sectional study was conducted with 7119 healthy Iranian participants (3525 males and 3594 females) aged 10-89 years. Seventeen hand-forearm anthropometric dimensions were measured by JEGS digital caliper and a measuring tape. Tip-to-tip, key and three-jaw chuck pinches were measured using a calibrated pinch gauge. Subsequently, 21 features pertinent to socio-demographic factors and hand-forearm anthropometric dimensions were used for classification. Furthermore, 12 well-known classifiers were implemented and evaluated to predict pinches. Results. Among the 21 features considered in this study, hand length, stature, age, thumb length and index finger length were found to be the most relevant and effective components for each of the three pinch predictions. The k-nearest neighbor, adaptive boosting (AdaBoost) and random forest classifiers achieved the highest classification accuracy of 96.75, 86.49 and 84.66% to predict three pinches, respectively. Conclusions. Predicting pinch strength and determining the predictive hand-forearm anthropometric and socio-demographic characteristics using ML may pave the way to designing an enhanced tool handle and reduce common musculoskeletal disorders of the hand.

Hierarchical superstructure aerogels for in situ biofluid metabolomics

High-throughput biofluid metabolomics analysis for screening life-threatening diseases is urgently needed. However, the high salt content of biofluid samples, which introduces severe interference, can greatly limit the analysis throughput. Here, a new 3-D interconnected hierarchical superstructure, namely a "plasmonic gold-on-silica (Au/SiO2) double-layered aerogel", integrating distinctive features of an upper plasmonic gold aerogel with a lower inert silica aerogel was successfully developed to achieve in situ separation and storage of inorganic salts in the silica aerogel, parallel enrichment of metabolites on the surface of the functionalized gold aerogel, and direct desorption/ionization of enriched metabolites by the photo-excited gold aerogel for rapid, sensitive, and comprehensive metabolomics analysis of human serum/urine samples. By integrating all these unique advantages into the hierarchical aerogel, multifunctional properties were introduced in the SALDI substrate to enable its effective utilization in clinical metabolomics for the discovery of reliable metabolic biomarkers to achieve unambiguous differentiation of early and advanced-stage lung cancer patients from healthy individuals. This study provides insight into the design and application of superstructured nanomaterials for in situ separation, storage, and photoexcitation of multi-components in complex biofluid samples for sensitive analysis.

Unraveling the distinction between depression and anxiety: A machine learning exploration of causal relationships

OBJECTIVE

Depression and anxiety, prevalent coexisting mood disorders, pose a clinical challenge in accurate differentiation, hindering effective healthcare interventions. This research addressed this gap by employing a streamlined Symptom Checklist 90 (SCL-90) designed to minimize patient response burden. Utilizing machine learning algorithms, the study sought to construct classification models capable of distinguishing between depression and anxiety.

METHODS

The study included 4262 individuals currently experiencing depression alone (n = 2998), anxiety alone (n = 716), or both depression and anxiety (n = 548). Counterfactual diagnosis was used to construct a causal network on the dataset. Employing a causal network, the SCL-90 was simplified. Items that have causality with only depression, only anxiety and both depression and anxiety were selected, and these streamlined items served as input features for four distinct machine learning algorithms, facilitating the creation of classification models for distinguishing depression and anxiety.

RESULTS

Cross-validation demonstrated the performance of the classification models with the following metrics: (1) K-nearest neighbors (AUC = 0.924, Acc = 92.81 %); (2) support vector machine (AUC = 0.937, Acc = 94.38 %); (3) random forest (AUC = 0.918, Acc = 94.38 %); and (4) adaptive boosting (AUC = 0.882, Acc = 94.38 %). Notably, the support vector machine excelled, with the highest AUC and superior accuracy.

CONCLUSION

Incorporating the simplified SCL-90 and machine learning presents a promising, efficient, and cost-effective tool for the precise identification of depression and anxiety.

Data Science Applications in Circular Economy: Trends, Status, and Future

The circular economy (CE) aims to decouple the growth of the economy from the consumption of finite resources through strategies, such as eliminating waste, circulating materials in use, and regenerating natural systems. Due to the rapid development of data science (DS), promising progress has been made in the transition toward CE in the past decade. DS offers various methods to achieve accurate predictions, accelerate product sustainable design, prolong asset life, optimize the infrastructure needed to circulate materials, and provide evidence-based insights. Despite the exciting scientific advances in this field, there still lacks a comprehensive review on this topic to summarize past achievements, synthesize knowledge gained, and navigate future research directions. In this paper, we try to summarize how DS accelerated the transition to CE. We conducted a critical review of where and how DS has helped the CE transition with a focus on four areas including (1) characterizing socioeconomic metabolism, (2) reducing unnecessary waste generation by enhancing material efficiency and optimizing product design, (3) extending product lifetime through repair, and (4) facilitating waste reuse and recycling. We also introduced the limitations and challenges in the current applications and discussed opportunities to provide a clear roadmap for future research in this field.

The path from task-specific to general purpose artificial intelligence for medical diagnostics: A bibliometric analysis

Artificial intelligence (AI) has revolutionized many fields, and its potential in healthcare has been increasingly recognized. Based on diverse data sources such as imaging, laboratory tests, medical records, and electrophysiological data, diagnostic AI has witnessed rapid development in recent years. A comprehensive understanding of the development status, contributing factors, and their relationships in the application of AI to medical diagnostics is essential to further promote its use in clinical practice. In this study, we conducted a bibliometric analysis to explore the evolution of task-specific to general-purpose AI for medical diagnostics. We used the Web of Science database to search for relevant articles published between 2010 and 2023, and applied VOSviewer, the R package Bibliometrix, and CiteSpace to analyze collaborative networks and keywords. Our analysis revealed that the field of AI in medical diagnostics has experienced rapid growth in recent years, with a focus on tasks such as image analysis, disease prediction, and decision support. Collaborative networks were observed among researchers and institutions, indicating a trend of global cooperation in this field. Additionally, we identified several key factors contributing to the development of AI in medical diagnostics, including data quality, algorithm design, and computational power. Challenges to progress in the field include model explainability, robustness, and equality, which will require multi-stakeholder, interdisciplinary collaboration to tackle. Our study provides a holistic understanding of the path from task-specific, mono-modal AI toward general-purpose, multimodal AI for medical diagnostics. With the continuous improvement of AI technology and the accumulation of medical data, we believe that AI will play a greater role in medical diagnostics in the future.

Progress on network modeling and analysis of gut microecology: a review

The gut microecological network is a complex microbial community within the human body that plays a key role in linking dietary nutrition and host physiology. To understand the complex relationships among microbes and their functions within this community, network analysis has emerged as a powerful tool. By representing the interactions between microbes and their associated omics data as a network, we can gain a comprehensive understanding of the ecological mechanisms that drive the human gut microbiota. In addition, the network-based approach provides a more intuitive analysis of the gut microbiota, simplifying the study of its complex dynamics and interdependencies. This review provides a comprehensive overview of the methods used to construct and analyze networks in the context of gut microecological background. We discuss various types of network modeling approaches, including co-occurrence networks, causal networks, dynamic networks, and multi-omics networks, and describe the analytical techniques used to identify important network properties. We also highlight the challenges and limitations of network modeling in this area, such as data scarcity and heterogeneity, and provide future research directions to overcome these limitations. By exploring these network-based methods, researchers can gain valuable insights into the intricate relationships and functional roles of microbial communities within the gut, ultimately advancing our understanding of the gut microbiota's impact on human health.

Fault diagnosis based on counterfactual inference for the batch fermentation process

Fault diagnosis plays a pivotal role in identifying the root causes of a fault. Current fault diagnosis methods encounter the shortcomings being unable to assess the fault amplitude or having low efficiency for batch fermentation process. In order to solve the above problems, this paper proposes a fault detection model named convolutional neural network based on variational autoencoder (CNN-VAE) and a fault diagnosis based on counterfactual inference (FDCI). To begin with, quality-related process variables are selected using mutual information (MI). Next, a two-dimensional moving window is used to obtain input sequences from the process data. Then, two statistics from the latent and residual domains of the CNN-VAE model are constructed for fault detection. Additionally, once a fault occurs, FDCI is used to locate the root cause of a fault. Finally, a simulation process and a real-world L. plantarum batch fermentation process are provided to demonstrate the effectiveness of the proposed approache.

AI in medical diagnosis: AI prediction & human judgment

AI has long been regarded as a panacea for decision-making and many other aspects of knowledge work; as something that will help humans get rid of their shortcomings. We believe that AI can be a useful asset to support decision-makers, but not that it should replace decision-makers. Decision-making uses algorithmic analysis, but it is not solely algorithmic analysis; it also involves other factors, many of which are very human, such as creativity, intuition, emotions, feelings, and value judgments. We have conducted semi-structured open-ended research interviews with 17 dermatologists to understand what they expect from an AI application to deliver to medical diagnosis. We have found four aggregate dimensions along which the thinking of dermatologists can be described: the ways in which our participants chose to interact with AI, responsibility, 'explainability', and the new way of thinking (mindset) needed for working with AI. We believe that our findings will help physicians who might consider using AI in their diagnosis to understand how to use AI beneficially. It will also be useful for AI vendors in improving their understanding of how medics want to use AI in diagnosis. Further research will be needed to examine if our findings have relevance in the wider medical field and beyond.

Automated graptolite identification at high taxonomic resolution using residual networks

Graptolites, fossils significant for evolutionary studies and shale gas exploration, are traditionally identified visually by taxonomists due to their intricate morphologies and preservation challenges. Artificial intelligence (AI) holds great promise for transforming such meticulous tasks. In this paper, we demonstrate that graptolites can be identified with taxonomist accuracy using a deep learning model. We construct the most sophisticated and largest professional single organisms image dataset to date, which is composed of >34,000 images of 113 graptolite species annotated at pixel-level resolution to train the model, develop, and evaluate deep learning networks to classify graptolites. The model's performance surpassed taxonomists in accuracy, time, and generalization, achieving 86% and 81% accuracy in identifying graptolite genus and species, respectively. This AI-based method, capable of recognizing minute morphological details better than taxonomists, can be integrated into web and mobile apps, extending graptolite identification beyond research institutes and enhancing shale gas exploration efficiency.

Novel ensemble learning approach with SVM-imputed ADASYN features for enhanced cervical cancer prediction

Cervical cancer remains a leading cause of female mortality, particularly in developing regions, underscoring the critical need for early detection and intervention guided by skilled medical professionals. While Pap smear images serve as valuable diagnostic tools, many available datasets for automated cervical cancer detection contain missing data, posing challenges for machine learning models' efficacy. To address these hurdles, this study presents an automated system adept at managing missing information using ADASYN characteristics, resulting in exceptional accuracy. The proposed methodology integrates a voting classifier model harnessing the predictive capacity of three distinct machine learning models. It further incorporates SVM Imputer and ADASYN up-sampled features to mitigate missing value concerns, while leveraging CNN-generated features to augment the model's capabilities. Notably, this model achieves remarkable performance metrics, boasting a 99.99% accuracy, precision, recall, and F1 score. A comprehensive comparative analysis evaluates the proposed model against various machine learning algorithms across four scenarios: original dataset usage, SVM imputation, ADASYN feature utilization, and CNN-generated features. Results indicate the superior efficacy of the proposed model over existing state-of-the-art techniques. This research not only introduces a novel approach but also offers actionable suggestions for refining automated cervical cancer detection systems. Its impact extends to benefiting medical practitioners by enabling earlier detection and improved patient care. Furthermore, the study's findings have substantial societal implications, potentially reducing the burden of cervical cancer through enhanced diagnostic accuracy and timely intervention.

Chinese experts' consensus on the application of intensive care big data

The development of intensive care medicine is inseparable from the diversified monitoring data. Intensive care medicine has been closely integrated with data since its birth. Critical care research requires an integrative approach that embraces the complexity of critical illness and the computational technology and algorithms that can make it possible. Considering the need of standardization of application of big data in intensive care, Intensive Care Medicine Branch of China Health Information and Health Care Big Data Society, Standard Committee has convened expert group, secretary group and the external audit expert group to formulate Chinese Experts' Consensus on the Application of Intensive Care Big Data (2022). This consensus makes 29 recommendations on the following five parts: Concept of intensive care big data, Important scientific issues, Standards and principles of database, Methodology in solving big data problems, Clinical application and safety consideration of intensive care big data. The consensus group believes this consensus is the starting step of application big data in the field of intensive care. More explorations and big data based retrospective research should be carried out in order to enhance safety and reliability of big data based models of critical care field.

Introduction to Computational Biomedicine

The domain of computational biomedicine is a new and burgeoning one. Its areas of concern cover all scales of human biology, physiology, and pathology, commonly referred to as medicine, from the genomic to the whole human and beyond, including epidemiology and population health. Computational biomedicine aims to provide high-fidelity descriptions and predictions of the behavior of biomedical systems of both fundamental scientific and clinical importance. Digital twins and virtual humans aim to reproduce the extremely accurate duplicate of real-world human beings in cyberspace, which can be used to make highly accurate predictions that take complicated conditions into account. When that can be done reliably enough for the predictions to be actionable, such an approach will make an impact in the pharmaceutical industry by reducing or even replacing the extremely laboratory-intensive preclinical process of making and testing compounds in laboratories, and in clinical applications by assisting clinicians to make diagnostic and treatment decisions.

Optimizing diabetes classification with a machine learning-based framework

BACKGROUND

Diabetes is a metabolic disorder usually caused by insufficient secretion of insulin from the pancreas or insensitivity of cells to insulin, resulting in long-term elevated blood sugar levels in patients. Patients usually present with frequent urination, thirst, and hunger. If left untreated, it can lead to various complications that can affect essential organs and even endanger life. Therefore, developing an intelligent diagnosis framework for diabetes is necessary.

RESULT

This paper proposes a machine learning-based diabetes classification framework machine learning optimized GAN. The framework encompasses several methodological approaches to address the diverse challenges encountered during the analysis. These approaches encompass the implementation of the mean and median joint filling method for handling missing values, the application of the cap method for outlier processing, and the utilization of SMOTEENN to mitigate sample imbalance. Additionally, the framework incorporates the employment of the proposed Diabetes Classification Model based on Generative Adversarial Network and employs logistic regression for detailed feature analysis. The effectiveness of the framework is evaluated using both the PIMA dataset and the diabetes dataset obtained from the GEO database. The experimental findings showcase our model achieved exceptional results, including a binary classification accuracy of 96.27%, tertiary classification accuracy of 99.31%, precision and f1 score of 0.9698, recall of 0.9698, and an AUC of 0.9702.

CONCLUSION

The experimental results show that the framework proposed in this paper can accurately classify diabetes and provide new ideas for intelligent diagnosis of diabetes.

Systematic review: fluid biomarkers and machine learning methods to improve the diagnosis from mild cognitive impairment to Alzheimer's disease

Mild cognitive impairment (MCI) is often considered an early stage of dementia, with estimated rates of progression to dementia up to 80-90% after approximately 6 years from the initial diagnosis. Diagnosis of cognitive impairment in dementia is typically based on clinical evaluation, neuropsychological assessments, cerebrospinal fluid (CSF) biomarkers, and neuroimaging. The main goal of diagnosing MCI is to determine its cause, particularly whether it is due to Alzheimer's disease (AD). However, only a limited percentage of the population has access to etiological confirmation, which has led to the emergence of peripheral fluid biomarkers as a diagnostic tool for dementias, including MCI due to AD. Recent advances in biofluid assays have enabled the use of sophisticated statistical models and multimodal machine learning (ML) algorithms for the diagnosis of MCI based on fluid biomarkers from CSF, peripheral blood, and saliva, among others. This approach has shown promise for identifying specific causes of MCI, including AD. After a PRISMA analysis, 29 articles revealed a trend towards using multimodal algorithms that incorporate additional biomarkers such as neuroimaging, neuropsychological tests, and genetic information. Particularly, neuroimaging is commonly used in conjunction with fluid biomarkers for both cross-sectional and longitudinal studies. Our systematic review suggests that cost-effective longitudinal multimodal monitoring data, representative of diverse cultural populations and utilizing white-box ML algorithms, could be a valuable contribution to the development of diagnostic models for AD due to MCI. Clinical assessment and biomarkers, together with ML techniques, could prove pivotal in improving diagnostic tools for MCI due to AD.

Machine learning model for the prediction of gram-positive and gram-negative bacterial bloodstream infection based on routine laboratory parameters

BACKGROUND

Bacterial bloodstream infection is responsible for the majority of cases of sepsis and septic shock. Early recognition of the causative pathogen is pivotal for administration of adequate empiric antibiotic therapy and for the survival of the patients. In this study, we developed a feasible machine learning (ML) model to predict gram-positive and gram-negative bacteremia based on routine laboratory parameters.

METHODS

Data for 2118 patients with bacteremia were obtained from the Medical Information Mart for Intensive Care dataset. Patients were randomly split into the training set and test set by stratified sampling, and 374 routine laboratory blood test variables were retrieved. Variables with missing values in more than 40% of the patients were excluded. Pearson correlation test was employed to eliminate redundant features. Five ML algorithms were used to build the model based on the selected features. Additionally, 132 patients with bacteremia who were treated at Qilu Hospital of Shandong University were included in an independent test cohort to evaluate the model.

RESULTS

After feature selection, 32 variables remained. All the five ML algorithms performed well in terms of discriminating between gram-positive and gram-negative bacteremia, but the performance of convolutional neural network (CNN) and random forest (RF) were better than other three algorithms. Consider of the interpretability of models, RF was chosen for further test (ROC-AUC = 0.768; 95%CI = 0.715-0.798, with a sensitivity of 75.20% and a specificity of 63.79%). To expand the application of the model, a decision tree (DT) was built utilizing the major variables, and it achieved an AUC of 0.679 (95%CI = 0.632-0.723), a sensitivity of 66%, and a specificity of 67.82% in the test cohort. When tested in the Qilu Hospital cohort, the ROC-AUC of the RF and DT models were 0.666 (95%CI = 0.579-0.746) and 0.615 (95%CI = 0.526-0.698), respectively. Finally, a software was developed to make the RF- and DT-based prediction models easily accessible.

CONCLUSION

The present ML-based models could effectively discriminate between gram-positive and gram-negative bacteremia based on routine laboratory blood test results. This simple model would be beneficial in terms of guiding timely antibiotic selection and administration in critically ill patients with bacteremia before their pathogen test results are available.

Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases: A Systematic Review

Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying lung sounds. ML models require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, and data sources of existing models in the literature. Papers published from five major databases between 1990 and 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The review encompassed 62 studies utilizing ML models and public-access databases for lung sound classification. Artificial neural networks (ANN) and support vector machines (SVM) were frequently employed in the ML classifiers. The accuracy ranged from 49.43% to 100% for discriminating abnormal sound types and 69.40% to 99.62% for disease class classification. Seventeen public databases were identified, with the ICBHI 2017 database being the most used (66%). The majority of studies exhibited a high risk of bias and concerns related to patient selection and reference standards. Summarizing, ML models can effectively classify abnormal lung sounds using publicly available data sources. Nevertheless, inconsistent reporting and methodologies pose limitations to advancing the field, and therefore, public databases should adhere to standardized recording and labeling procedures.

Neuroimaging Scoring Tools to Differentiate Inflammatory Central Nervous System Small-Vessel Vasculitis: A Need for Artificial Intelligence/Machine Learning?-A Scoping Review

Neuroimaging has a key role in identifying small-vessel vasculitis from common diseases it mimics, such as multiple sclerosis. Oftentimes, a multitude of these conditions present similarly, and thus diagnosis is difficult. To date, there is no standardized method to differentiate between these diseases. This review identifies and presents existing scoring tools that could serve as a starting point for integrating artificial intelligence/machine learning (AI/ML) into the clinical decision-making process for these rare diseases. A scoping literature review of EMBASE and MEDLINE included 114 articles to evaluate what criteria exist to diagnose small-vessel vasculitis and common mimics. This paper presents the existing criteria of small-vessel vasculitis conditions and mimics them to guide the future integration of AI/ML algorithms to aid in diagnosing these conditions, which present similarly and non-specifically.

Machine Learning Algorithms Applied to Predict Autism Spectrum Disorder Based on Gut Microbiome Composition

The application of machine learning (ML) techniques stands as a reliable method for aiding in the diagnosis of complex diseases. Recent studies have related the composition of the gut microbiota to the presence of autism spectrum disorder (ASD), but until now, the results have been mostly contradictory. This work proposes using machine learning to study the gut microbiome composition and its role in the early diagnosis of ASD. We applied support vector machines (SVMs), artificial neural networks (ANNs), and random forest (RF) algorithms to classify subjects as neurotypical (NT) or having ASD, using published data on gut microbiome composition. Naive Bayes, k-nearest neighbors, ensemble learning, logistic regression, linear regression, and decision trees were also trained and validated; however, the ones presented showed the best performance and interpretability. All the ML methods were developed using the SAS Viya software platform. The microbiome's composition was determined using 16S rRNA sequencing technology. The application of ML yielded a classification accuracy as high as 90%, with a sensitivity of 96.97% and specificity reaching 85.29%. In the case of the ANN model, no errors occurred when classifying NT subjects from the first dataset, indicating a significant classification outcome compared to traditional tests and data-based approaches. This approach was repeated with two datasets, one from the USA and the other from China, resulting in similar findings. The main predictors in the obtained models differ between the analyzed datasets. The most important predictors identified from the analyzed datasets are Bacteroides, Lachnospira, Anaerobutyricum, and Ruminococcus torques. Notably, among the predictors in each model, there is the presence of bacteria that are usually considered insignificant in the microbiome's composition due to their low relative abundance. This outcome reinforces the conventional understanding of the microbiome's influence on ASD development, where an imbalance in the composition of the microbiota can lead to disrupted host-microbiota homeostasis. Considering that several previous studies focused on the most abundant genera and neglected smaller (and frequently not statistically significant) microbial communities, the impact of such communities has been poorly analyzed. The ML-based models suggest that more research should focus on these less abundant microbes. A novel hypothesis explains the contradictory results in this field and advocates for more in-depth research to be conducted on variables that may not exhibit statistical significance. The obtained results seem to contribute to an explanation of the contradictory findings regarding ASD and its relation with gut microbiota composition. While some research correlates higher ratios of Bacillota/Bacteroidota, others find the opposite. These discrepancies are closely linked to the minority organisms in the microbiome's composition, which may differ between populations but share similar metabolic functions. Therefore, the ratios of Bacillota/Bacteroidota regarding ASD may not be determinants in the manifestation of ASD.

Redesigning Primary Care: The Emergence of Artificial-Intelligence-Driven Symptom Diagnostic Tools

Modern healthcare is facing a juxtaposition of increasing patient demands owing to an aging population and a decreasing general practitioner workforce, leading to strained access to primary care. The coronavirus disease 2019 pandemic has emphasized the potential for alternative consultation methods, highlighting opportunities to minimize unnecessary care. This article discusses the role of artificial-intelligence-driven symptom checkers, particularly their efficiency, utility, and challenges in primary care. Based on a study conducted in Italian general practices, insights from both physicians and patients were gathered regarding this emergent technology, highlighting differences in perceived utility, user satisfaction, and potential challenges. While symptom checkers are seen as potential tools for addressing healthcare challenges, concerns regarding their accuracy and the potential for misdiagnosis persist. Patients generally viewed them positively, valuing their ease of use and the empowerment they provide in managing health. However, some general practitioners perceive these tools as challenges to their expertise. This article proposes that artificial-intelligence-based symptom checkers can optimize medical-history taking for the benefit of both general practitioners and patients, with potential enhancements in complex diagnostic tasks rather than routine diagnoses. It underscores the importance of carefully integrating digital innovations while preserving the essential human touch in healthcare. Symptom checkers offer promising solutions; ensuring their accuracy, reliability, and effective integration into primary care requires rigorous research, clinical guidance, and an understanding of varied user perceptions. Collaboration among technologists, clinicians, and patients is paramount for the successful evolution of digital tools in healthcare.

Sentiment analysis in multilingual context: Comparative analysis of machine learning and hybrid deep learning models

This research paper investigates the efficacy of various machine learning models, including deep learning and hybrid models, for text classification in the English and Bangla languages. The study focuses on sentiment analysis of comments from a popular Bengali e-commerce site, "DARAZ," which comprises both Bangla and translated English reviews. The primary objective of this study is to conduct a comparative analysis of various models, evaluating their efficacy in the domain of sentiment analysis. The research methodology includes implementing seven machine learning models and deep learning models, such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Convolutional 1D (Conv1D), and a combined Conv1D-LSTM. Preprocessing techniques are applied to a modified text set to enhance model accuracy. The major conclusion of the study is that Support Vector Machine (SVM) models exhibit superior performance compared to other models, achieving an accuracy of 82.56% for English text sentiment analysis and 86.43% for Bangla text sentiment analysis using the porter stemming algorithm. Additionally, the Bi-LSTM Based Model demonstrates the best performance among the deep learning models, achieving an accuracy of 78.10% for English text and 83.72% for Bangla text using porter stemming. This study signifies significant progress in natural language processing research, particularly for Bangla, by enhancing improved text classification models and methodologies. The results of this research make a significant contribution to the field of sentiment analysis and offer valuable insights for future research and practical applications.

Artificial intelligence can dynamically adjust strategies for auxiliary diagnosing respiratory diseases and analyzing potential pathological relationships

Respiratory diseases are one of the leading causes of human death and exacerbate the global burden of non-communicable diseases. Finding a method to assist clinicians pre-diagnose these diseases is an urgent task. Existing artificial intelligence-based methods can improve the clinical diagnosis efficiency, but still face challenges. For example, the lack of interpretability, the problem of information redundancy or missing caused by only using static data, the difficulty of model to learn the interdependence between features, and the performance of model is limited by sparse datasets, etc. To alleviate these problems, we propose a novel RQPA-Net. It consists of Q&A diagnosis module (QAD) and pathological inference module (PI). The QAD is responsible for interacting with patients, adjusting inquiry strategies dynamically and collecting effective information for disease diagnosis. The designed multi-subspace network can alleviate the problem that classical method is difficult to understand the interdependence between features. The deep reinforcement learning designed also can alleviate the problem of classical methods lack of interpretability. The PI is responsible for reasoning potential pathological relationships between diseases or symptoms based on existing knowledge. Through integrating the advantages of deep learning and reinforcement learning techniques, PI can handle sparse datasets. Finally, for auxiliary diagnosis, the model achieves 0.9780 ± 0.0002 Recall, 0.9778 ± 0.0003 Acc, 0.9779 ± 0.0003 Precision and 0.9780 ± 0.0003 F1-score on the test set. In terms of assisting pathological analysis, compared with the end-to-end model, our model achieves higher comprehensive performance on different tasks and datasets with different degrees of sparsity. Even in sparse datasets, it can effectively infer potential associations between diseases or symptoms, and has higher potential clinical application. In this paper, we propose a novel network structure, which can not only assist doctors in diagnosing diseases, but also contribute to explore the potential disease mechanisms. It provides a new perspective for integrating AI technology and clinical practice.

Assessing the transportability of clinical prediction models for cognitive impairment using causal models

BACKGROUND

Machine learning models promise to support diagnostic predictions, but may not perform well in new settings. Selecting the best model for a new setting without available data is challenging. We aimed to investigate the transportability by calibration and discrimination of prediction models for cognitive impairment in simulated external settings with different distributions of demographic and clinical characteristics.

METHODS

We mapped and quantified relationships between variables associated with cognitive impairment using causal graphs, structural equation models, and data from the ADNI study. These estimates were then used to generate datasets and evaluate prediction models with different sets of predictors. We measured transportability to external settings under guided interventions on age, APOE ε4, and tau-protein, using performance differences between internal and external settings measured by calibration metrics and area under the receiver operating curve (AUC).

RESULTS

Calibration differences indicated that models predicting with causes of the outcome were more transportable than those predicting with consequences. AUC differences indicated inconsistent trends of transportability between the different external settings. Models predicting with consequences tended to show higher AUC in the external settings compared to internal settings, while models predicting with parents or all variables showed similar AUC.

CONCLUSIONS

We demonstrated with a practical prediction task example that predicting with causes of the outcome results in better transportability compared to anti-causal predictions when considering calibration differences. We conclude that calibration performance is crucial when assessing model transportability to external settings.

Discovering genetic biomarkers for targeted cancer therapeutics with eXplainable AI

Explainable Artificial Intelligence (XAI) enables a holistic understanding of the complex and nonlinear relationships between genes and prognostic outcomes of cancer patients. In this study, we focus on a distinct aspect of XAI - to generate accurate and biologically relevant hypotheses and provide a shorter and more creative path to advance medical research. We present an XAI-driven approach to discover otherwise unknown genetic biomarkers as potential therapeutic targets in high-grade serous ovarian cancer, evidenced by the discovery of IL27RA, which leads to reduced peritoneal metastases when knocked down in tumor-carrying mice given IL27-siRNA-DOPC nanoparticles.

Summary

Explainable Artificial Intelligence is amenable to generating biologically relevant testable hypotheses despite their limitations due to explanations originating from post hoc realizations.

Machine Learning with Alpha Toxin Phenotype to Predict Clinical Outcome in Patients with Staphylococcus aureus Bloodstream Infection

Staphylococcus aureus bloodstream (SAB) infection remains a leading cause of sepsis-related mortality. Yet, current treatment does not account for variable virulence traits that mediate host dysregulated immune response, such as SA α-toxin (Hla)-mediated thrombocytopenia. Here, we applied machine learning (ML) to bacterial growth images combined with platelet count data to predict patient outcomes. We profiled Hla phenotypes of SA isolates collected from patients with bacteremia by taking smartphone images of beta-hemolytic growth on sheep blood agar (SBA). Electronic medical records were reviewed to extract relevant laboratory and clinical data. A convolutional neural network was applied to process the plate image data for input along with day 1 patient platelet count to generate ML-based models that predict thrombocytopenia on day 4 and mortality. A total of 229 patients infected with SA strains exhibiting varying zone sizes of beta-hemolysis on SBA were included. A total of 539 images of bacterial growth on SBA were generated as inputs for model development. One-third of patients developed thrombocytopenia at onset, with an overall mortality rate of 18.8%. The models developed from the ML algorithm showed strong performance (AUC 0.92) for predicting thrombocytopenia on day 4 of infection and modest performance (AUC 0.711) for mortality. Our findings support further development and validation of a proof-of-concept ML application in digital microbiology, with a measure of bacterial virulence factor production that carries prognostic significance and can help guide treatment selection.

Optical Diffractive Convolutional Neural Networks Implemented in an All-Optical Way

Optical neural networks can effectively address hardware constraints and parallel computing efficiency issues inherent in electronic neural networks. However, the inability to implement convolutional neural networks at the all-optical level remains a hurdle. In this work, we propose an optical diffractive convolutional neural network (ODCNN) that is capable of performing image processing tasks in computer vision at the speed of light. We explore the application of the 4f system and the diffractive deep neural network (D2NN) in neural networks. ODCNN is then simulated by combining the 4f system as an optical convolutional layer and the diffractive networks. We also examine the potential impact of nonlinear optical materials on this network. Numerical simulation results show that the addition of convolutional layers and nonlinear functions improves the classification accuracy of the network. We believe that the proposed ODCNN model can be the basic architecture for building optical convolutional networks.

Understanding multimorbidity requires sign-disease networks and higher-order interactions, a perspective

Background

Count scores, disease clustering, and pairwise associations between diseases remain ubiquitous in multimorbidity research despite two major shortcomings: they yield no insight into plausible mechanisms underlying multimorbidity, and they ignore higher-order interactions such as effect modification.

Objectives

We argue that two components are currently missing but vital to develop novel multimorbidity metrics. Firstly, networks should be constructed which consists simultaneously of signs, symptoms, and diseases, since only then could they yield insight into plausible shared biological mechanisms underlying diseases.Secondly, learning pairwise associations is insufficient to fully characterize the correlations in a system. That is, synergistic (e.g., cooperative or antagonistic) effects are widespread in complex systems, where two or more elements combined give a larger or smaller effect than the sum of their individual effects. It can even occur that pairs of symptoms have no pairwise associations whatsoever, but in combination have a significant association. Therefore, higher-order interactions should be included in networks used to study multimorbidity, resulting in so-called hypergraphs.

Methods

We illustrate our argument using a synthetic Bayesian Network model of symptoms, signs and diseases, composed of pairwise and higher-order interactions. We simulate network interventions on both individual and population levels and compare the ground-truth outcomes with the predictions from pairwise associations.

Conclusion

We find that, when judged purely from the pairwise associations, interventions can have unexpected 'side-effects' or the most opportune intervention could be missed. The hypergraph uncovers links missed in pairwise networks, giving a more complete overview of sign and disease associations.

Deep bidirectional LSTM for disease classification supporting hospital admission based on pre-diagnosis: a case study in Vietnam

Overcrowding in hospitals in Vietnam has caused many disadvantages in receiving and treating patients. Especially at the stage of receiving and diagnosing procedures taking patients to the treatment departments in the hospital takes up much time. This study proposes a text-based disease diagnosis using text processing techniques (such as Bag of Words, Term Frequency- Inverse Document Frequency, and Tokenizer) combined with classifiers (such as Random Forests (RF), Multi-Layer Perceptron (MLP), Embeddings and Bidirectional Long Short-term memory (LSTM)) on symptoms. As observed from the results, deep Bidirectional LSTM can reach 0.982 in AUC in the classification of 10 diseases on 230,457 samples of pre-diagnosis collected from Vietnam hospitals used in the training and testing phases. The proposed approach is expected to provide a way to automate patient flow in hospitals to improve healthcare in the future.

Physicians' Perspectives on a Multi-Dimensional Model for the Roles of Electronic Health Records in Approaching a Proper Differential Diagnosis

Many healthcare organizations have adopted Electronic Health Records (EHRs) to improve the quality of care and help physicians make proper clinical decisions. The vital roles of EHRs can support the accuracy of diagnosis, suggest, and rationalize the provided care to patients. This study aims to understand the roles of EHRs in approaching proper differential diagnosis and optimizing patient safety. This study utilized a cross-sectional survey-based descriptive research design to assess physicians' perceptions of the roles of EHRs on diagnosis quality and safety. Physicians working in tertiary hospitals in Saudi Arabia were surveyed. Three hundred and fifty-one participants were included in the study, of which 61% were male. The main participants were family/general practice (22%), medicine, general (14%), and OB/GYN (12%). Overall, 66% of the participants ranked themselves as IT competent, most of the participants underwent IT self-guided learning, and 65% of the participants always used the system. The results generally reveal positive physicians' perceptions toward the roles of the EHR system on diagnosis quality and safety. There was a statistically significant relationship between user characteristics and the roles of the EHR by enhancing access to care, patient-physician encounter, clinical reasoning, diagnostic testing and consultation, follow-up, and diagnostic safety functionality. The study participants demonstrate positive perceptions of physicians toward the roles of the EHR system in approaching differential diagnosis. Yet, areas of improvement in the design and using EHRs are emphasized.

Difficult diagnosis in the ICU: making the right call but beware uncertainty and bias

Dealing with an uncertain or missed diagnosis is commonplace in the intensive care unit setting. Affected patients are subject to a potential decrease in quality of care and a greater risk of a poor outcome. The diagnostic process is a complex task that starts with information gathering, followed by integration and interpretation of data, hypothesis generation and, finally, confirmation of a (hopefully correct) diagnosis. This may be particularly challenging in the patient who is critically ill where a good history may not be forthcoming and/or clinical, laboratory and imaging features are non-specific. The aim of this narrative review is to analyse and describe common causes of diagnostic error in the intensive care unit, highlighting the multiple types of cognitive bias, and to suggest a diagnostic framework. To inform this review, we performed a literature search to identify relevant articles, particularly those pertinent to unclear diagnoses in patients who are critically ill. Clinicians should be cognisant as to how they formulate diagnoses and utilise debiasing strategies. Multidisciplinary teamwork and more time spent with the patient, supported by effective and efficient use of electronic healthcare records and decision support resources, is likely to improve the quality of the diagnostic process, patient care and outcomes.

Modeling COVID-19 disease processes by remote elicitation of causal Bayesian networks from medical experts

BACKGROUND

COVID-19 is a new multi-organ disease causing considerable worldwide morbidity and mortality. While many recognized pathophysiological mechanisms are involved, their exact causal relationships remain opaque. Better understanding is needed for predicting their progression, targeting therapeutic approaches, and improving patient outcomes. While many mathematical causal models describe COVID-19 epidemiology, none have described its pathophysiology.

METHODS

In early 2020, we began developing such causal models. The SARS-CoV-2 virus's rapid and extensive spread made this particularly difficult: no large patient datasets were publicly available; the medical literature was flooded with sometimes conflicting pre-review reports; and clinicians in many countries had little time for academic consultations. We used Bayesian network (BN) models, which provide powerful calculation tools and directed acyclic graphs (DAGs) as comprehensible causal maps. Hence, they can incorporate both expert opinion and numerical data, and produce explainable, updatable results. To obtain the DAGs, we used extensive expert elicitation (exploiting Australia's exceptionally low COVID-19 burden) in structured online sessions. Groups of clinical and other specialists were enlisted to filter, interpret and discuss the literature and develop a current consensus. We encouraged inclusion of theoretically salient latent (unobservable) variables, likely mechanisms by extrapolation from other diseases, and documented supporting literature while noting controversies. Our method was iterative and incremental: systematically refining and validating the group output using one-on-one follow-up meetings with original and new experts. 35 experts contributed 126 hours face-to-face, and could review our products.

RESULTS

We present two key models, for the initial infection of the respiratory tract and the possible progression to complications, as causal DAGs and BNs with corresponding verbal descriptions, dictionaries and sources. These are the first published causal models of COVID-19 pathophysiology.

CONCLUSIONS

Our method demonstrates an improved procedure for developing BNs via expert elicitation, which other teams can implement to model emergent complex phenomena. Our results have three anticipated applications: (i) freely disseminating updatable expert knowledge; (ii) guiding design and analysis of observational and clinical studies; (iii) developing and validating automated tools for causal reasoning and decision support. We are developing such tools for the initial diagnosis, resource management, and prognosis of COVID-19, parameterized using the ISARIC and LEOSS databases.

Artificial Intelligence for Dementia Research Methods Optimization

INTRODUCTION

Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS

We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS

We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION

ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.