Integrating Machine Learning with Human Knowledge

DIGIPREDICT: physiological, behavioural and environmental predictors of asthma attacks-a prospective observational study using digital markers and artificial intelligence-study protocol

INTRODUCTION

Asthma attacks are a leading cause of morbidity and mortality but are preventable in most if detected and treated promptly. However, the changes that occur physiologically and behaviourally in the days and weeks preceding an attack are not always recognised, highlighting a potential role for technology. The aim of this study 'DIGIPREDICT' is to identify early digital markers of asthma attacks using sensors embedded in smart devices including watches and inhalers, and leverage health and environmental datasets and artificial intelligence, to develop a risk prediction model to provide an early, personalised warning of asthma attacks.

METHODS AND ANALYSIS

A prospective sample of 300 people, 12 years or older, with a history of a moderate or severe asthma attack in the last 12 months will be recruited in New Zealand. Each participant will be given a smart watch (to assess physiological measures such as heart and respiratory rate), peak flow meter, smart inhaler (to assess adherence and inhalation) and a cough monitoring application to use regularly over 6 months with fortnightly questionnaires on asthma control and well-being. Data on sociodemographics, asthma control, lung function, dietary intake, medical history and technology acceptance will be collected at baseline and at 6 months. Asthma attacks will be measured by self-report and confirmed with clinical records. The collected data, along with environmental data on weather and air quality, will be analysed using machine learning to develop a risk prediction model for asthma attacks.

ETHICS AND DISSEMINATION

Ethical approval has been obtained from the New Zealand Health and Disability Ethics Committee (2023 FULL 13541). Enrolment began in August 2023. Results will be presented at local, national and international meetings, including dissemination via community groups, and submission for publication to peer-reviewed journals.

TRIAL REGISTRATION NUMBER

Australian New Zealand Clinical Trials Registry ACTRN12623000764639; Australian New Zealand Clinical Trials Registry.

Towards proactive palliative care in oncology: developing an explainable EHR-based machine learning model for mortality risk prediction

BACKGROUND

Ex-ante identification of the last year in life facilitates a proactive palliative approach. Machine learning models trained on electronic health records (EHR) demonstrate promising performance in cancer prognostication. However, gaps in literature include incomplete reporting of model performance, inadequate alignment of model formulation with implementation use-case, and insufficient explainability hindering trust and adoption in clinical settings. Hence, we aim to develop an explainable machine learning EHR-based model that prompts palliative care processes by predicting for 365-day mortality risk among patients with advanced cancer within an outpatient setting.

METHODS

Our cohort consisted of 5,926 adults diagnosed with Stage 3 or 4 solid organ cancer between July 1, 2017, and June 30, 2020 and receiving ambulatory cancer care within a tertiary center. The classification problem was modelled using Extreme Gradient Boosting (XGBoost) and aligned to our envisioned use-case: "Given a prediction point that corresponds to an outpatient cancer encounter, predict for mortality within 365-days from prediction point, using EHR data up to 365-days prior." The model was trained with 75% of the dataset (n = 39,416 outpatient encounters) and validated on a 25% hold-out dataset (n = 13,122 outpatient encounters). To explain model outputs, we used Shapley Additive Explanations (SHAP) values. Clinical characteristics, laboratory tests and treatment data were used to train the model. Performance was evaluated using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC), while model calibration was assessed using the Brier score.

RESULTS

In total, 17,149 of the 52,538 prediction points (32.6%) had a mortality event within the 365-day prediction window. The model demonstrated an AUROC of 0.861 (95% CI 0.856-0.867) and AUPRC of 0.771. The Brier score was 0.147, indicating slight overestimations of mortality risk. Explanatory diagrams utilizing SHAP values allowed visualization of feature impacts on predictions at both the global and individual levels.

CONCLUSION

Our machine learning model demonstrated good discrimination and precision-recall in predicting 365-day mortality risk among individuals with advanced cancer. It has the potential to provide personalized mortality predictions and facilitate earlier integration of palliative care.

Artificial intelligence and open science in discovery of disease-modifying medicines for Alzheimer's disease

The high failure rate of clinical trials in Alzheimer's disease (AD) and AD-related dementia (ADRD) is due to a lack of understanding of the pathophysiology of disease, and this deficit may be addressed by applying artificial intelligence (AI) to "big data" to rapidly and effectively expand therapeutic development efforts. Recent accelerations in computing power and availability of big data, including electronic health records and multi-omics profiles, have converged to provide opportunities for scientific discovery and treatment development. Here, we review the potential utility of applying AI approaches to big data for discovery of disease-modifying medicines for AD/ADRD. We illustrate how AI tools can be applied to the AD/ADRD drug development pipeline through collaborative efforts among neurologists, gerontologists, geneticists, pharmacologists, medicinal chemists, and computational scientists. AI and open data science expedite drug discovery and development of disease-modifying therapeutics for AD/ADRD and other neurodegenerative diseases.

Single-residue linear and conformational B cell epitopes prediction using random and ESM-2 based projections

B cell epitope prediction methods are separated into linear sequence-based predictors and conformational epitope predictions that typically use the measured or predicted protein structure. Most linear predictions rely on the translation of the sequence to biologically based representations and the applications of machine learning on these representations. We here present CALIBER 'Conformational And LInear B cell Epitopes pRediction', and show that a bidirectional long short-term memory with random projection produces a more accurate prediction (test set AUC=0.789) than all current linear methods. The same predictor when combined with an Evolutionary Scale Modeling-2 projection also improves on the state of the art in conformational epitopes (AUC = 0.776). The inclusion of the graph of the 3D distances between residues did not increase the prediction accuracy. However, the long-range sequence information was essential for high accuracy. While the same model structure was applicable for linear and conformational epitopes, separate training was required for each. Combining the two slightly increased the linear accuracy (AUC 0.775 versus 0.768) and reduced the conformational accuracy (AUC = 0.769).

Clinical decision support system using a machine learning model to assist simultaneous cardiopulmonary auscultation: Open-label randomized controlled trial

Background

The utility of a clinical decision support system using a machine learning (ML) model for simultaneous cardiac and pulmonary auscultation is unknown.

Objective

This study aimed to develop and evaluate an ML system's utility for cardiopulmonary auscultation.

Methods

First, we developed an ML system for cardiopulmonary auscultation, using cardiopulmonary sound files from our previous study. The technique involved pre-processing, feature extraction, and classification through several neural network layers. After integration, the output class was categorized as "normal," "abnormal," or "undetermined." Second, we evaluated the ML system with 24 junior residents in an open-label randomized controlled trial at a university hospital. Participants were randomly assigned to the ML system group (intervention) or conventional auscultation group (control). During training, participants listened to four cardiac and four pulmonary sounds, all of which were correctly classified. Then, participants classified a series of 16 simultaneous cardiopulmonary sounds. The control group auscultated the sounds using noise-cancelling headphones, while the intervention group did so by watching recommendations from the ML system.

Results

The total scores for correctly identified normal or abnormal cardiopulmonary sounds in the intervention group were significantly higher than those in the control group (366/384 [95.3%] vs. 343/384 [89.3%], P = 0.003). The cardiac test score in the intervention group was better (111/192 [57.8%] vs. 90/192 [46.9%], P = 0.04); there was no significant difference in pulmonary auscultation.

Conclusions

The ML-based system improved the accuracy of cardiopulmonary auscultation for junior residents. This result suggests that the system can assist early-career physicians in accurate screening.

A framework for integrating artificial intelligence for clinical care with continuous therapeutic monitoring

The complex relationships between continuously monitored health signals and therapeutic regimens can be modelled via machine learning. However, the clinical implementation of the models will require changes to clinical workflows. Here we outline ClinAIOps ('clinical artificial-intelligence operations'), a framework that integrates continuous therapeutic monitoring and the development of artificial intelligence (AI) for clinical care. ClinAIOps leverages three feedback loops to enable the patient to make treatment adjustments using AI outputs, the clinician to oversee patient progress with AI assistance, and the AI developer to receive continuous feedback from both the patient and the clinician. We lay out the central challenges and opportunities in the deployment of ClinAIOps by means of examples of its application in the management of blood pressure, diabetes and Parkinson's disease. By enabling more frequent and accurate measurements of a patient's health and more timely adjustments to their treatment, ClinAIOps may substantially improve patient outcomes.

The applications of machine learning techniques in medical data processing based on distributed computing and the Internet of Things

Medical data processing has grown into a prominent topic in the latest decades with the primary goal of maintaining patient data via new information technologies, including the Internet of Things (IoT) and sensor technologies, which generate patient indexes in hospital data networks. Innovations like distributed computing, Machine Learning (ML), blockchain, chatbots, wearables, and pattern recognition can adequately enable the collection and processing of medical data for decision-making in the healthcare era. Particularly, to assist experts in the disease diagnostic process, distributed computing is beneficial by digesting huge volumes of data swiftly and producing personalized smart suggestions. On the other side, the current globe is confronting an outbreak of COVID-19, so an early diagnosis technique is crucial to lowering the fatality rate. ML systems are beneficial in aiding radiologists in examining the incredible amount of medical images. Nevertheless, they demand a huge quantity of training data that must be unified for processing. Hence, developing Deep Learning (DL) confronts multiple issues, such as conventional data collection, quality assurance, knowledge exchange, privacy preservation, administrative laws, and ethical considerations. In this research, we intend to convey an inclusive analysis of the most recent studies in distributed computing platform applications based on five categorized platforms, including cloud computing, edge, fog, IoT, and hybrid platforms. So, we evaluated 27 articles regarding the usage of the proposed framework, deployed methods, and applications, noting the advantages, drawbacks, and the applied dataset and screening the security mechanism and the presence of the Transfer Learning (TL) method. As a result, it was proved that most recent research (about 43%) used the IoT platform as the environment for the proposed architecture, and most of the studies (about 46%) were done in 2021. In addition, the most popular utilized DL algorithm was the Convolutional Neural Network (CNN), with a percentage of 19.4%. Hence, despite how technology changes, delivering appropriate therapy for patients is the primary aim of healthcare-associated departments. Therefore, further studies are recommended to develop more functional architectures based on DL and distributed environments and better evaluate the present healthcare data analysis models.

Machine learning-based protein signatures for differentiating hypertensive disorders of pregnancy

Hypertensive disorders of pregnancy (HDP) result in major maternal and fetal complications. Our study aimed to find a panel of protein markers to identify HDP by applying machine-learning models. The study was conducted on a total of 133 samples, divided into four groups, healthy pregnancy (HP, n = 42), gestational hypertension (GH, n = 67), preeclampsia (PE, n = 9), and ante-partum eclampsia (APE, n = 15). Thirty circulatory protein markers were measured using Luminex multiplex immunoassay and ELISA. Significant markers were screened for potential predictive markers by both statistical and machine-learning approaches. Statistical analysis found seven markers such as sFlt-1, PlGF, endothelin-1(ET-1), basic-FGF, IL-4, eotaxin and RANTES to be altered significantly in disease groups compared to healthy pregnant. Support vector machine (SVM) learning model classified GH and HP with 11 markers (eotaxin, GM-CSF, IL-4, IL-6, IL-13, MCP-1, MIP-1α, MIP-1β, RANTES, ET-1, sFlt-1) and HDP with 13 markers (eotaxin, G-CSF, GM-CSF, IFN-gamma, IL-4, IL-5, IL-6, IL-13, MCP-1, MIP-1β, RANTES, ET-1, sFlt-1). While logistic regression (LR) model classified PE with 13 markers (basic FGF, IL-1β, IL-1ra, IL-7, IL-9, MIP-1β, RANTES, TNF-alpha, nitric oxide, superoxide dismutase, ET-1, PlGF, sFlt-1) and APE by 12 markers (eotaxin, basic-FGF, G-CSF, GM-CSF, IL-1β, IL-5, IL-8, IL-13, IL-17, PDGF-BB, RANTES, PlGF). These markers may be used to diagnose the progression of healthy pregnant to a hypertensive state. Future longitudinal studies with large number of samples are needed to validate these findings.

Forecasting actual evapotranspiration without climate data based on stacked integration of DNN and meta-heuristic models across China from 1958 to 2021

As a non-linear phenomenon that varies along with agro-climatic conditions alongside many other factors, Evapotranspiration (ET) process represents a complexity when be assessed especially if there is a data scarcity in the weather data. However, even under such a data scarcity, the accurate estimates of ET values remain necessary for precise irrigation. So, the present study aims to: i) evaluate the performance of six hybrid machine learning (ML) models in estimating the monthly actual ET values under different agro-climatic conditions in China for seven provinces (Shandong, Jiangsu, Zhejiang, Fujian, Jiangxi, Hubei, and Henan), and ii) select the best-developed model based on statistical metrics and reduce errors between predicted and actual ET (AET) values. AET datasets were divided into 78% for model training (from 1958 to 2007) and the remaining was used for testing (from 2008 to 2021). Deep Neural Networks (DNN) was used as a standalone model at first then the stacking method was applied to integrate DNN with data-driven models such as Additive regression (AR), Random Forest (RF), Random Subspace (RSS), M5 Burned Tree (M5P) and Reduced Error Purning Tree (REPTree). Partial Auto-Correlation Function (PACF) was used for selection of the best lags inputs to the developed models. Results have revealed that DNN-based hybrid models held better performance than non-hybrid DNN models, such that the DNN-RF algorithm outperformed others during both training and testing stages, followed by DNN-RSS. This model has acquired the best values of every statistical measure [MAE (10.8, 12.9), RMSE (15.6, 17.4), RAE (31.9%, 41.4%), and RRSE (39.3%, 47.2%)] for training and testing, respectively. In contrast, the DNN model held the worst performance [MAE (14.9, 13.7), RMSE (20.1, 18.2), RAE (43.9%, 43.7%), and RRSE (50.6%, 49.3%)], for training and testing, respectively. Results from the study presented have revealed the capability of DNN-based hybrid models for long-term predictions of the AET values. Moreover, the DNN-RF model has been suggested as the most suitable model to improve future investigation for AET predictions, which could benefit the enhancement of the irrigation process and increase crop yield.

Neuroevolution-Based Network Architecture Evolution in Semiconductor Manufacturing

Promoted model architectures or algorithms are crucial for intelligent manufacturing since developing them takes a lot of trial and error to embed the domain knowledge into the models correctly. Especially in semiconductor manufacturing, the whole processes depend on complicated physical equations and sophisticated fine-tuning. Therefore, we use a neuroevolution-based model to search the optimized architecture automatically. The collector current value at a particular bias of the silicon-germanium (SiGe) heterojunction bipolar transistor, generated by technology computer-aided design (TCAD), is used as the target dataset with six process parameters as the inputs. The processes include oxidation, dry and wet etching, implantation, annealing, diffusion, and chemical-mechanical polishing. Our work can build a suitable model network with a fast turnaround time, and practical physical constraints are fused in it without domain knowledge extraction. Take the case with 3840 data and one output as an instance. The mean square errors of the train set and validation set, as well as the mean absolute percentage error of the test set, are 1.317 × 10-6, 7.215 × 10-7, and 0.216 while using multilayer perceptron (MLP) and they are 3.285 × 10-7, 1.661 × 10-7, and 0.097 while using NE. The consequences show that the work in this vein is promising. According to the trend plot and results, the ability to extract physic is much better than the traditional (MLP) model.

Environmental insults and compensative responses: when microbiome meets cancer

Tumor microenvironment has recently been ascribed a new hallmark-the polymorphic microbiome. Accumulating evidence regarding the tissue specific territories of tumor-microbiome have opened new and interesting avenues. A pertinent question is regarding the functional consequence of the interface between host-microbiome and cancer. Given microbial communities have predominantly been explored through an ecological perspective, it is important that the foundational aspects of ecological stress and the fight to 'survive and thrive' are accounted for tumor-micro(b)environment as well. Building on existing evidence and classical microbial ecology, here we attempt to characterize the ecological stresses and the compensative responses of the microorganisms inside the tumor microenvironment. What insults would microbes experience inside the cancer jungle? How would they respond to these insults? How the interplay of stress and microbial quest for survival would influence the fate of tumor? This work asks these questions and tries to describe this underdiscussed ecological interface of the tumor and its microbiota. It is hoped that a larger scientific thought on the importance of microbial competition sensing vis-à-vis tumor-microenvironment would be stimulated.

Machine learning versus crop growth models: an ally, not a rival

The rapid increases of the global population and climate change pose major challenges to a sustainable production of food to meet consumer demands. Process-based models (PBMs) have long been used in agricultural crop production for predicting yield and understanding the environmental regulation of plant physiological processes and its consequences for crop growth and development. In recent years, with the increasing use of sensor and communication technologies for data acquisition in agriculture, machine learning (ML) has become a popular tool in yield prediction (especially on a large scale) and phenotyping. Both PBMs and ML are frequently used in studies on major challenges in crop production and each has its own advantages and drawbacks. We propose to combine PBMs and ML given their intrinsic complementarity, to develop knowledge- and data-driven modelling (KDDM) with high prediction accuracy as well as good interpretability. Parallel, serial and modular structures are three main modes can be adopted to develop KDDM for agricultural applications. The KDDM approach helps to simplify model parameterization by making use of sensor data and improves the accuracy of yield prediction. Furthermore, the KDDM approach has great potential to expand the boundary of current crop models to allow upscaling towards a farm, regional or global level and downscaling to the gene-to-cell level. The KDDM approach is a promising way of combining simulation models in agriculture with the fast developments in data science while mechanisms of many genetic and physiological processes are still under investigation, especially at the nexus of increasing food production, mitigating climate change and achieving sustainability.

Machine learning for nanoplasmonics

Plasmonic nanomaterials have outstanding optoelectronic properties potentially enabling the next generation of catalysts, sensors, lasers and photothermal devices. Owing to optical and electron techniques, modern nanoplasmonics research generates large datasets characterizing features across length scales. Furthermore, optimizing syntheses leading to specific nanostructures requires time-consuming multiparametric approaches. These complex datasets and trial-and-error practices make nanoplasmonics research ripe for the application of machine learning (ML) and advanced data processing methods. ML algorithms capture relationships between synthesis, structure and performance in a way that far exceeds conventional simulation and theory approaches, enabling effective performance optimization. For example, neural networks can tailor the nanostructure morphology to target desired properties, identify synthetic conditions and extract quantitative information from complex data. Here we discuss the nascent field of ML for nanoplasmonics, describe the opportunities and limitations of ML in nanoplasmonic research, and conclude that ML is potentially transformative, especially if the community curates and shares its big data.

The Value of the First Clinical Impression as Assessed by 18 Observations in Patients Presenting to the Emergency Department

The first clinical impression of emergency patients conveys a myriad of information that has been incompletely elucidated. In this prospective, observational study, the value of the first clinical impression, assessed by 18 observations, to predict the need for timely medical attention, the need for hospital admission, and in-hospital mortality in 1506 adult patients presenting to the triage desk of an emergency department was determined. Machine learning models were used for statistical analysis. The first clinical impression could predict the need for timely medical attention [area under the receiver operating characteristic curve (AUC ROC), 0.73; p = 0.01] and hospital admission (AUC ROC, 0.8; p = 0.004), but not in-hospital mortality (AUC ROC, 0.72; p = 0.13). The five most important features informing the prediction models were age, ability to walk, admission by emergency medical services, lying on a stretcher, breathing pattern, and bringing a suitcase. The inability to walk at triage presentation was highly predictive of both the need for timely medical attention (p < 0.001) and the need for hospital admission (p < 0.001). In conclusion, the first clinical impression of emergency patients presenting to the triage desk can predict the need for timely medical attention and hospital admission. Important components of the first clinical impression were identified.

Elicitation of domain knowledge for a machine learning model for paediatric critical illness in South Africa

Objectives

Delays in identification, resuscitation and referral have been identified as a preventable cause of avoidable severity of illness and mortality in South African children. To address this problem, a machine learning model to predict a compound outcome of death prior to discharge from hospital and/or admission to the PICU was developed. A key aspect of developing machine learning models is the integration of human knowledge in their development. The objective of this study is to describe how this domain knowledge was elicited, including the use of a documented literature search and Delphi procedure.

Design

A prospective mixed methodology development study was conducted that included qualitative aspects in the elicitation of domain knowledge, together with descriptive and analytical quantitative and machine learning methodologies.

Setting

A single centre tertiary hospital providing acute paediatric services.

Participants

Three paediatric intensivists, six specialist paediatricians and three specialist anaesthesiologists.

Interventions

None.

Measurements and main results

The literature search identified 154 full-text articles reporting risk factors for mortality in hospitalised children. These factors were most commonly features of specific organ dysfunction. 89 of these publications studied children in lower- and middle-income countries. The Delphi procedure included 12 expert participants and was conducted over 3 rounds. Respondents identified a need to achieve a compromise between model performance, comprehensiveness and veracity and practicality of use. Participants achieved consensus on a range of clinical features associated with severe illness in children. No special investigations were considered for inclusion in the model except point-of-care capillary blood glucose testing. The results were integrated by the researcher and a final list of features was compiled.

Conclusion

The elicitation of domain knowledge is important in effective machine learning applications. The documentation of this process enhances rigour in such models and should be reported in publications. A documented literature search, Delphi procedure and the integration of the domain knowledge of the researchers contributed to problem specification and selection of features prior to feature engineering, pre-processing and model development.

Incorporation of Human Knowledge into Data Embeddings to Improve Pattern Significance and Interpretability

Embedding is a common technique for analyzing multi-dimensional data. However, the embedding projection cannot always form significant and interpretable visual structures that foreshadow underlying data patterns. We propose an approach that incorporates human knowledge into data embeddings to improve pattern significance and interpretability. The core idea is (1) externalizing tacit human knowledge as explicit sample labels and (2) adding a classification loss in the embedding network to encode samples' classes. The approach pulls samples of the same class with similar data features closer in the projection, leading to more compact (significant) and class-consistent (interpretable) visual structures. We give an embedding network with a customized classification loss to implement the idea and integrate the network into a visualization system to form a workflow that supports flexible class creation and pattern exploration. Patterns found on open datasets in case studies, subjects' performance in a user study, and quantitative experiment results illustrate the general usability and effectiveness of the approach.

Stress granules dynamics: benefits in cancer

Stress granules (SGs) are stress-induced subcellular compartments, which carry out a particular function to cope with stress. These granules protect cells from stress-related damage and cell death through dynamic sequestration of numerous ribonucleoproteins (RNPs) and signaling proteins, thereby promoting cell survival under both physiological and pathological condition. During tumorigenesis, cancer cells are repeatedly exposed to diverse stress stimuli from the tumor microenvironment, and the dynamics of SGs is often modulated due to the alteration of gene expression patterns in cancer cells, leading to tumor progression as well as resistance to anticancer treatment. In this mini review, we provide a brief discussion about our current understanding of the fundamental roles of SGs during physiological stress and the effect of dysregulated SGs on cancer cell fitness and cancer therapy. [BMB Reports 2022; 55(12): 577-586].

A scoping review on the use of natural language processing in research on political polarization: trends and research prospects

As part of the "text-as-data" movement, Natural Language Processing (NLP) provides a computational way to examine political polarization. We conducted a methodological scoping review of studies published since 2010 (n = 154) to clarify how NLP research has conceptualized and measured political polarization, and to characterize the degree of integration of the two different research paradigms that meet in this research area. We identified biases toward US context (59%), Twitter data (43%) and machine learning approach (33%). Research covers different layers of the political public sphere (politicians, experts, media, or the lay public), however, very few studies involved more than one layer. Results indicate that only a few studies made use of domain knowledge and a high proportion of the studies were not interdisciplinary. Those studies that made efforts to interpret the results demonstrated that the characteristics of political texts depend not only on the political position of their authors, but also on other often-overlooked factors. Ignoring these factors may lead to overly optimistic performance measures. Also, spurious results may be obtained when causal relations are inferred from textual data. Our paper provides arguments for the integration of explanatory and predictive modeling paradigms, and for a more interdisciplinary approach to polarization research.

Supplementary Information

The online version contains supplementary material available at 10.1007/s42001-022-00196-2.

Stress granules dynamics: benefits in cancer

Stress granules (SGs) are stress-induced subcellular compartments, which carry out a particular function to cope with stress. These granules protect cells from stress-related damage and cell death through dynamic sequestration of numerous ribonucleoproteins (RNPs) and signaling proteins, thereby promoting cell survival under both physiological and pathological condition. During tumorigenesis, cancer cells are repeatedly exposed to diverse stress stimuli from the tumor microenvironment, and the dynamics of SGs is often modulated due to the alteration of gene expression patterns in cancer cells, leading to tumor progression as well as resistance to anticancer treatment. In this mini review, we provide a brief discussion about our current understanding of the fundamental roles of SGs during physiological stress and the effect of dysregulated SGs on cancer cell fitness and cancer therapy. [BMB Reports 2022; 55(12): 577-586].

Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Natural disasters always have a damaging effect on our way of life. Landslides  cause serious damage to both human and natural resources around the world. In this paper, the prediction accuracy of five hybrid models for landslide occurrence in the Uttarkashi, Uttarakhand (India) was evaluated and compared. In this approach, the Rough Set theory coupled with five different models namely Bayesian Network (HBNRS), Backpropagation Neural Network (HBPNNRS), Bagging (HBRS), XGBoost (HXGBRS), and Random Forest (HRFRS) were taken into account. The database for the models development was prepared using fifteen conditioning factors that had 373 landslide and 181 non-landslide locations that were then randomly divided into training and testing locations with a ratio of 75%:25%. The appropriateness and predictability of these conditioning factors were assessed using the multi-collinearity test and the least absolute shrinkage and selection operator approach. The accuracy, sensitivity, specificity, precision, and F-Measures, and the area under the curve (AUC)-receiver operating characteristics curve, were used to evaluate and compare the performance of the individual and hybrid created models. The findings indicate that the constructed hybrid model HXGBRS (AUC = 0.937, Precision = 0.946, F1-score = 0.926 and Accuracy = 89.92%) is the most accurate model for predicting landslides when compared to other models (HBPNNRS, HBNRS, HBRS, and HRFRS). Importantly, when the fusion is performed with the rough set method, the prediction capability of each model is improved. Simultaneously, the HXGBRS model proposed shows superior stability and can effectively avoid overfitting. After the core modules were developed, the user-friendly platform was designed as an integrated GIS environment using dynamic maps for effective landslide prediction in large prone areas. Users can predict the probability of landslide occurrence for selected region by changing the values of a conditioning factors. The created approach could be beneficial for predicting the impact of landslides on slopes and tracking landslides along national routes.

Prior Knowledge for Predictive Modeling: The Case of Acute Aquatic Toxicity

Early assessment of the potential impact of chemicals on health and the environment requires toxicological properties of the molecules. Predictive modeling is often used to estimate the property values in silico from pre-existing experimental data, which is often scarce and uncertain. One of the ways to advance the predictive modeling procedure might be the use of knowledge existing in the field. Scientific publications contain a vast amount of knowledge. However, the amount of manual work required to process the enormous volumes of information gathered in scientific articles might hinder its utilization. This work explores the opportunity of semiautomated knowledge extraction from scientific papers and investigates a few potential ways of its use for predictive modeling. The knowledge extraction and predictive modeling are applied to the field of acute aquatic toxicity. Acute aquatic toxicity is an important parameter of the safety assessment of chemicals. The extensive amount of diverse information existing in the field makes acute aquatic toxicity an attractive area for investigation of knowledge use for predictive modeling. The work demonstrates that the knowledge collection and classification procedure could be useful in hybrid modeling studies concerning the model and predictor selection, addressing data gaps, and evaluation of models’ performance.

Identification of microstructures critically affecting material properties using machine learning framework based on metallurgists’ thinking process

In materials science, machine learning has been intensively researched and used in various applications. However, it is still far from achieving intelligence comparable to that of human experts in terms of creativity and explainability. In this paper, we investigate whether machine learning can acquire explainable knowledge without directly introducing problem-specific information such as explicit physical mechanisms. In particular, a potential of machine learning to obtain the capability to identify a part of material structures that critically affects a physical property without human prior knowledge is mainly discussed. The guide for constructing the machine learning framework adopted in this paper is to imitate human researchers’ process of thinking in the interpretation and development of materials. Our framework was applied to the optimization of structures of artificial dual-phase steels in terms of a fracture property. A comparison of results of the framework with those of numerical simulation based on governing physical laws demonstrated the potential of our framework for the identification of a part of microstructures critically affecting the target property. Consequently, this implies that our framework can implicitly acquire an intuition in a similar way that human researchers empirically attain the general strategy for material design consistent with the physical background.

Predicting reaction conditions from limited data through active transfer learning

Transfer and active learning have the potential to accelerate the development of new chemical reactions, using prior data and new experiments to inform models that adapt to the target area of interest. This article shows how specifically tuned machine learning models, based on random forest classifiers, can expand the applicability of Pd-catalyzed cross-coupling reactions to types of nucleophiles unknown to the model. First, model transfer is shown to be effective when reaction mechanisms and substrates are closely related, even when models are trained on relatively small numbers of data points. Then, a model simplification scheme is tested and found to provide comparative predictivity on reactions of new nucleophiles that include unseen reagent combinations. Lastly, for a challenging target where model transfer only provides a modest benefit over random selection, an active transfer learning strategy is introduced to improve model predictions. Simple models, composed of a small number of decision trees with limited depths, are crucial for securing generalizability, interpretability, and performance of active transfer learning.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

Potential benefits and limitations of machine learning in the field of eating disorders: current research and future directions

Advances in machine learning and digital data provide vast potential for mental health predictions. However, research using machine learning in the field of eating disorders is just beginning to emerge. This paper provides a narrative review of existing research and explores potential benefits, limitations, and ethical considerations of using machine learning to aid in the detection, prevention, and treatment of eating disorders. Current research primarily uses machine learning to predict eating disorder status from females' responses to validated surveys, social media posts, or neuroimaging data often with relatively high levels of accuracy. This early work provides evidence for the potential of machine learning to improve current eating disorder screening methods. However, the ability of these algorithms to generalise to other samples or be used on a mass scale is only beginning to be explored. One key benefit of machine learning over traditional statistical methods is the ability of machine learning to simultaneously examine large numbers (100s to 1000s) of multimodal predictors and their complex non-linear interactions, but few studies have explored this potential in the field of eating disorders. Machine learning is also being used to develop chatbots to provide psychoeducation and coping skills training around body image and eating disorders, with implications for early intervention. The use of machine learning to personalise treatment options, provide ecological momentary interventions, and aid the work of clinicians is also discussed. Machine learning provides vast potential for the accurate, rapid, and cost-effective detection, prevention, and treatment of eating disorders. More research is needed with large samples of diverse participants to ensure that machine learning models are accurate, unbiased, and generalisable to all people with eating disorders. There are important limitations and ethical considerations with utilising machine learning methods in practice. Thus, rather than a magical solution, machine learning should be seen as an important tool to aid the work of researchers, and eventually clinicians, in the early identification, prevention, and treatment of eating disorders.

Assessing Changes in Mountain Treeline Ecotones over 30 Years Using CNNs and Historical Aerial Images

Historical black-and-white (B&W) aerial images have been recognized as an important source of information for assessing vegetation dynamics. However, the use of these images is limited by the lack of multispectral information, as well as by their varying quality. It is therefore important to study and develop methods that are capable of automatic and accurate classification of these B&W images while reducing the need for tedious manual work. The goal of this study was to assess changes over 30 years in woody vegetation cover along alpine treeline ecotones using B&W aerial images from two time points. A convolutional neural networks model was firstly set up based on three structure classes calculated from Airborne Laser Scanning data using the B&W aerial images from 2010. Then, the model was improved by active addition of training samples of those that were wrongly predicted from historical B&W aerial images from 1980. A comparison with visual image interpretation revealed generally high agreement for the class “dense forest” and lower agreement for the class “group of trees”. The study illustrates that vegetation changes at the treeline ecotone can be detected in order to assess areawide long-term vegetation dynamics at a fine spatial resolution.

A global picture: therapeutic perspectives for COVID-19

The COVID-19 pandemic is a lethal virus outbreak by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), which has severely affected human lives and the global economy. The most vital part of the research and development of therapeutic agents is to design drug products to manage COVID-19 efficiently. Numerous attempts have been in place to determine the optimal drug dose and combination of drugs to treat the disease on a global scale. This article documents the information available on SARS-CoV-2 and its life cycle, which will aid in the development of the potential treatment options. A consolidated summary of several natural and repurposed drugs to manage COVID-19 is depicted with summary of current vaccine development. People with high age, comorbity and concomitant illnesses such as overweight, metabolic disorders, pulmonary disease, coronary heart disease, renal failure, fatty liver and neoplastic disorders are more prone to create serious COVID-19 and its consequences. This article also presents an overview of post-COVID-19 complications in patients.

A global picture: therapeutic perspectives for COVID-19

The COVID-19 pandemic is a lethal virus outbreak by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), which has severely affected human lives and the global economy. The most vital part of the research and development of therapeutic agents is to design drug products to manage COVID-19 efficiently. Numerous attempts have been in place to determine the optimal drug dose and combination of drugs to treat the disease on a global scale. This article documents the information available on SARS-CoV-2 and its life cycle, which will aid in the development of the potential treatment options. A consolidated summary of several natural and repurposed drugs to manage COVID-19 is depicted with summary of current vaccine development. People with high age, comorbity and concomitant illnesses such as overweight, metabolic disorders, pulmonary disease, coronary heart disease, renal failure, fatty liver and neoplastic disorders are more prone to create serious COVID-19 and its consequences. This article also presents an overview of post-COVID-19 complications in patients.

Deep Phenotyping on Chinese Electronic Health Records by Recognizing Linguistic Patterns of Phenotypic Narratives with a Sequence Motif Discovery Tool: Algorithm Development and Validation (Preprint)

Background

Phenotype information in electronic health records (EHRs) is mainly recorded in unstructured free text, which cannot be directly used for clinical research. EHR-based deep-phenotyping methods can structure phenotype information in EHRs with high fidelity, making it the focus of medical informatics. However, developing a deep-phenotyping method for non-English EHRs (ie, Chinese EHRs) is challenging. Although numerous EHR resources exist in China, fine-grained annotation data that are suitable for developing deep-phenotyping methods are limited. It is challenging to develop a deep-phenotyping method for Chinese EHRs in such a low-resource scenario.

Objective

In this study, we aimed to develop a deep-phenotyping method with good generalization ability for Chinese EHRs based on limited fine-grained annotation data.

Methods

The core of the methodology was to identify linguistic patterns of phenotype descriptions in Chinese EHRs with a sequence motif discovery tool and perform deep phenotyping of Chinese EHRs by recognizing linguistic patterns in free text. Specifically, 1000 Chinese EHRs were manually annotated based on a fine-grained information model, PhenoSSU (Semantic Structured Unit of Phenotypes). The annotation data set was randomly divided into a training set (n=700, 70%) and a testing set (n=300, 30%). The process for mining linguistic patterns was divided into three steps. First, free text in the training set was encoded as single-letter sequences (P: phenotype, A: attribute). Second, a biological sequence analysis tool—MEME (Multiple Expectation Maximums for Motif Elicitation)—was used to identify motifs in the single-letter sequences. Finally, the identified motifs were reduced to a series of regular expressions representing linguistic patterns of PhenoSSU instances in Chinese EHRs. Based on the discovered linguistic patterns, we developed a deep-phenotyping method for Chinese EHRs, including a deep learning–based method for named entity recognition and a pattern recognition–based method for attribute prediction.

Results

In total, 51 sequence motifs with statistical significance were mined from 700 Chinese EHRs in the training set and were combined into six regular expressions. It was found that these six regular expressions could be learned from a mean of 134 (SD 9.7) annotated EHRs in the training set. The deep-phenotyping algorithm for Chinese EHRs could recognize PhenoSSU instances with an overall accuracy of 0.844 on the test set. For the subtask of entity recognition, the algorithm achieved an F1 score of 0.898 with the Bidirectional Encoder Representations from Transformers–bidirectional long short-term memory and conditional random field model; for the subtask of attribute prediction, the algorithm achieved a weighted accuracy of 0.940 with the linguistic pattern–based method.

Conclusions

We developed a simple but effective strategy to perform deep phenotyping of Chinese EHRs with limited fine-grained annotation data. Our work will promote the second use of Chinese EHRs and give inspiration to other non–English-speaking countries.

Artificial neural network-based smart aerogel glazing in low-energy buildings: A state-of-the-art review

Aerogel materials with super-insulating, visual-penetrable, and sound-proof properties are promising in buildings, whereas the coupling effect of various parameters in complex porous aerogels proposes challenges for thermal/visual performance prediction. Traditional physics-based models face challenges such as modeling complexity, heavy computational load, and inadaptability for long-term validation (owing to boundary condition change, degradation of thermophysical properties, and so on). In this study, a holistic review is conducted on aerogel production, components prefabrication, modeling development, single-, and multi-objective optimizations. Methodologies to quantify parameter uncertainties are reviewed, including interface energy balance, Rosseland approximation and Monte Carlo method. Novel aerogel integrated glazing systems with synergistic functions are demonstrated. Originalities include an innovative modeling approach, enhanced computational efficiency, and user-friendly interface for non-professionals or multidisciplinary research. In addition, human knowledge-based machine learning can reduce abundant data requirement, increase performance prediction reliability, and improve model interpretability, so as to promote advanced aerogel materials in smart and energy-efficient buildings.

Artificial intelligence for the early detection of colorectal cancer: A comprehensive review of its advantages and misconceptions

Colorectal cancer (CRC) was the second-ranked worldwide type of cancer during 2020 due to the crude mortality rate of 12.0 per 100000 inhabitants. It can be prevented if glandular tissue (adenomatous polyps) is detected early. Colonoscopy has been strongly recommended as a screening test for both early cancer and adenomatous polyps. However, it has some limitations that include the high polyp miss rate for smaller (< 10 mm) or flat polyps, which are easily missed during visual inspection. Due to the rapid advancement of technology, artificial intelligence (AI) has been a thriving area in different fields, including medicine. Particularly, in gastroenterology AI software has been included in computer-aided systems for diagnosis and to improve the assertiveness of automatic polyp detection and its classification as a preventive method for CRC. This article provides an overview of recent research focusing on AI tools and their applications in the early detection of CRC and adenomatous polyps, as well as an insightful analysis of the main advantages and misconceptions in the field.

In Search of a Unifying Concept in Human Diseases

Throughout the history of biological/medicine sciences, there has been opposing strategies to find solutions to complex human disease problems. Both empirical and deductive approaches have led to major insights and concepts that have led to practical preventive and therapeutic benefits for the human population. The classic definitions of "science" (to know) has been paired with the classic definition of technology (to do). One knew more as the technology developed, and that development was often based on science. In other words, one could do more if science could improve the technology. In turn, this made possible to know more science with improved technology. However, with the development of new technologies of today in biology and medicine, major advances have been made, such as the information from the Human Genome Project, genetic engineering techniques and the use of bioinformatic uses of sophisticated computer analyses. This has led to the renewed idea that Precision Medicine, while raising some serious ethical concerns, also raises the expectation of improved potential of risk predictions for prevention and treatment of various genetically and environmentally influenced human diseases. This new field Artificial Intelligence, as a major handmaiden to Precision Medicine, is significantly altering the fundamental means of biological discovery. However, can today's fundamental premise of "Artificial Intelligence", based on identifying DNA, as the primary nexus of human health and disease, provide the practical solutions to complex human diseases that involve the interaction of those genes with the broad spectrum of "environmental factors"? Will it be "precise" enough to provide practical solutions for prevention and treatments of diseases? In this "Commentary", with the example of human carcinogenesis, it will be challenged that, without the integration of mechanistic and hypothesis-driven approaches with the "unbiased" empirical analyses of large numbers of data, the Artificial Intelligence approach with fall short.

Informed Attentive Predictors: A Generalisable Architecture for Prior Knowledge-Based Assisted Diagnosis of Cancers

Due to the high mortality of many cancers and their related diseases, the prediction and prognosis techniques of cancers are being extensively studied to assist doctors in making diagnoses. Many machine-learning-based cancer predictors have been put forward, but many of them have failed to become widely utilised due to some crucial problems. For example, most methods require too much training data, which is not always applicable to institutes, and the complicated genetic mutual effects of cancers are generally ignored in many proposed methods. Moreover, a majority of these assist models are actually not safe to use, as they are generally built on black-box machine learners that lack references from related field knowledge. We observe that few machine-learning-based cancer predictors are capable of employing prior knowledge (PrK) to mitigate these issues. Therefore, in this paper, we propose a generalisable informed machine learning architecture named the Informed Attentive Predictor (IAP) to make PrK available to the predictor’s decision-making phases and apply it to the field of cancer prediction. Specifically, we make several implementations of the IAP and evaluate its performance on six TCGA datasets to demonstrate the effectiveness of our architecture as an assist system framework for actual clinical usage. The experimental results show a noticeable improvement in IAP models on accuracies, f1-scores and recall rates compared to their non-IAP counterparts (i.e., basic predictors).

Integrating domain knowledge with machine learning to detect obstructive sleep apnea: Snore as a significant bio-feature

Our study's main purpose is to emphasise the significance of medical knowledge of pathophysiology before machine learning. We investigated whether combining domain knowledge with machine learning results might increase accuracy and minimise the number of bio-features used to detect obstructive sleep apnea (OSA). The present study analysed data on 36 self-reported symptoms and 24 clinical features obtained from 3,495 patients receiving polysomnography at a regional hospital and a medical centre. The area under the receiver operating characteristic (AUC) curve was used to evaluate patients with and without moderate or severe OSA using three prediction models on the basis of various estimation methods: the multiple logistic regression (MLR), support vector machine (SVM), and neural network (NN) methods. Odds ratios stratified by gender and age were also measured to account for clinicians' common sense. We discovered that adding the self-reported snoring item improved the AUC by 0.01-0.10 and helped us to rapidly achieve the optimum level. The performance of four items (gender, age, body mass index [BMI], and snoring) was comparable with that of adding two or more items (neck and waist circumference) for predicting moderate to severe OSA (Apnea-Hypopnea Index ≥15 events/hr) in all three prediction models, demonstrating the medical knowledge value of pathophysiology. The four-item test sample AUCs were 0.83, 0.84, and 0.83 for MLR, SVM, and NN, respectively. Participants with regular snoring and a BMI of ≥25 kg/m² had a greater chance of moderate to severe OSA according to the stratified adjusted odds ratios. Combining domain knowledge into machine learning could increase efficiency and enable primary care physicians to refer for an OSA diagnosis earlier.

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

High-throughput image-based technologies are now widely used in the rapidly developing field of digital phenomics and are generating ever-increasing amounts and diversity of data. Artificial intelligence (AI) is becoming a game changer in turning the vast seas of data into valuable predictions and insights. However, this requires specialized programming skills and an in-depth understanding of machine learning, deep learning, and ensemble learning algorithms. Here, we attempt to methodically review the usage of different tools, technologies, and services available to the phenomics data community and show how they can be applied to selected problems in explainable AI-based image analysis. This tutorial provides practical and useful resources for novices and experts to harness the potential of the phenomic data in explainable AI-led breeding programs.

Evaluation of aspiration problems in L2 English pronunciation employing machine learning

The approach proposed in this study includes methods specifically dedicated to the detection of allophonic variation in English. This study aims to find an efficient method for automatic evaluation of aspiration in the case of Polish second-language (L2) English speakers' pronunciation when whole words are analyzed instead of particular allophones extracted from words. Sample words including aspirated and unaspirated allophones were prepared by experts in English phonetics and phonology. The datasets created include recordings of words pronounced by nine native English speakers of standard southern British accent and 20 Polish L2 English users. Complete unedited words are treated as input data for feature extraction and classification algorithms such as k-nearest neighbors, naive Bayes method, long-short term memory, and convolutional neural network (CNN). Various signal representations, including low-level audio features, the so-called mid-term and feature trajectory, and spectrograms, are tested in the context of their usability for the detection of aspiration. The results obtained show high potential for an automated evaluation of pronunciation focused on a particular phonological feature (aspiration) when classifiers analyze whole words. Additionally, CNN returns satisfying results for the automated classification of words containing aspirated and unaspirated allophones produced by Polish L2 speakers.

A deeper look into natural sciences with physics-based and data-driven measures

With the development of machine learning in recent years, it is possible to glean much more information from an experimental data set to study matter. In this perspective, we discuss some state-of-the-art data-driven tools to analyze latent effects in data and explain their applicability in natural science, focusing on two recently introduced, physics-motivated computationally cheap tools-latent entropy and latent dimension. We exemplify their capabilities by applying them on several examples in the natural sciences and show that they reveal so far unobserved features such as, for example, a gradient in a magnetic measurement and a latent network of glymphatic channels from the mouse brain microscopy data. What sets these techniques apart is the relaxation of restrictive assumptions typical of many machine learning models and instead incorporating aspects that best fit the dynamical systems at hand.

Artificial intelligence and machine learning for medical imaging: A technology review

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.

Machine learning toward advanced energy storage devices and systems

Technology advancement demands energy storage devices (ESD) and systems (ESS) with better performance, longer life, higher reliability, and smarter management strategy. Designing such systems involve a trade-off among a large set of parameters, whereas advanced control strategies need to rely on the instantaneous status of many indicators. Machine learning can dramatically accelerate calculations, capture complex mechanisms to improve the prediction accuracy, and make optimized decisions based on comprehensive status information. The computational efficiency makes it applicable for real-time management. This paper reviews recent progresses in this emerging area, especially new concepts, approaches, and applications of machine learning technologies for commonly used energy storage devices (including batteries, capacitors/supercapacitors, fuel cells, other ESDs) and systems (including battery ESS, hybrid ESS, grid and microgrid-containing energy storage units, pumped-storage system, thermal ESS). The perspective on future directions is also discussed.