Browse
Submit Data
Databases
API
Help

Dataset Information

14 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A comparison of explainable artificial intelligence methods in the phase classification of multi-principal element alloys.

ABSTRACT: We demonstrate the capabilities of two model-agnostic local post-hoc model interpretability methods, namely breakDown (BD) and shapley (SHAP), to explain the predictions of a black-box classification learning model that establishes a quantitative relationship between chemical composition and multi-principal element alloys (MPEA) phase formation. We trained an ensemble of support vector machines using a dataset with 1,821 instances, 12 features with low pair-wise correlation, and seven phase labels. Feature contributions to the model prediction are computed by BD and SHAP for each composition. The resulting BD and SHAP transformed data are then used as inputs to identify similar composition groups using k-means clustering. Explanation-of-clusters by features reveal that the results from SHAP agree more closely with the literature. Visualization of compositions within a cluster using Ceteris-Paribus (CP) profile plots show the functional dependencies between the feature values and predicted response. Despite the differences between BD and SHAP in variable attribution, only minor changes were observed in the CP profile plots. Explanation-of-clusters by examples show that the clusters that share a common phase label contain similar compositions, which clarifies the similar-looking CP profile trends. Two plausible reasons are identified to describe this observation: (1) In the limits of a dataset with independent and non-interacting features, BD and SHAP show promise in recognizing MPEA composition clusters with similar phase labels. (2) There is more than one explanation for the MPEA phase formation rules with respect to the set of features considered in this work.

SUBMITTER: Lee K

PROVIDER: S-EPMC9270422 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Origin of radiation resistance in multi-principal element alloys.

Project description:Using molecular dynamics simulations, we characterized the generation and evolution of radiation-induced point defects in the CoCrFeMnNi high-entropy alloy (HEA), to compare it with pure Ni and pure Fe. The generation of primary point defects was investigated by a cascade simulation at 773?K and the evolution of point defect clusters by a defect evolution simulation using 1 at% defect-containing samples. The numbers of residual defects after cascade and surviving defects after evolution in the CoCrFeMnNi HEA are smaller than those in pure Ni and pure Fe. The defect clusters appearing in the CoCrFeMnNi HEA after the defect evolution are unstable because of the alloy complexity. The origin of the slower radiation damage accumulation and the higher radiation damage tolerance in the CoCrFeMnNi HEA is discussed.

| S-EPMC6207767 | biostudies-literature

Ultrahigh-temperature melt printing of multi-principal element alloys.

Project description:Multi-principal element alloys (MPEA) demonstrate superior synergetic properties compared to single-element predominated traditional alloys. However, the rapid melting and uniform mixing of multi-elements for the fabrication of MPEA structural materials by metallic 3D printing is challenging as it is difficult to achieve both a high temperature and uniform temperature distribution in a sufficient heating source simultaneously. Herein, we report an ultrahigh-temperature melt printing method that can achieve rapid multi-elemental melting and uniform mixing for MPEA fabrication. In a typical fabrication process, multi-elemental metal powders are loaded into a high-temperature column zone that can be heated up to 3000 K via Joule heating, followed by melting on the order of milliseconds and mixing into homogenous alloys, which we attribute to the sufficiently uniform high-temperature heating zone. As proof-of-concept, we successfully fabricated single-phase bulk NiFeCrCo MPEA with uniform grain size. This ultrahigh-temperature rapid melt printing process provides excellent potential toward MPEA 3D printing.

| S-EPMC9640643 | biostudies-literature

Analyzing breast cancer invasive disease event classification through explainable artificial intelligence.

Project description:IntroductionRecently, accurate machine learning and deep learning approaches have been dedicated to the investigation of breast cancer invasive disease events (IDEs), such as recurrence, contralateral and second cancers. However, such approaches are poorly interpretable.MethodsThus, we designed an Explainable Artificial Intelligence (XAI) framework to investigate IDEs within a cohort of 486 breast cancer patients enrolled at IRCCS Istituto Tumori "Giovanni Paolo II" in Bari, Italy. Using Shapley values, we determined the IDE driving features according to two periods, often adopted in clinical practice, of 5 and 10 years from the first tumor diagnosis.ResultsAge, tumor diameter, surgery type, and multiplicity are predominant within the 5-year frame, while therapy-related features, including hormone, chemotherapy schemes and lymphovascular invasion, dominate the 10-year IDE prediction. Estrogen Receptor (ER), proliferation marker Ki67 and metastatic lymph nodes affect both frames.DiscussionThus, our framework aims at shortening the distance between AI and clinical practice.

| S-EPMC9932275 | biostudies-literature

Accelerated exploration of multi-principal element alloys with solid solution phases.

Project description:Recent multi-principal element, high entropy alloy (HEA) development strategies vastly expand the number of candidate alloy systems, but also pose a new challenge--how to rapidly screen thousands of candidate alloy systems for targeted properties. Here we develop a new approach to rapidly assess structural metals by combining calculated phase diagrams with simple rules based on the phases present, their transformation temperatures and useful microstructures. We evaluate over 130,000 alloy systems, identifying promising compositions for more time-intensive experimental studies. We find the surprising result that solid solution alloys become less likely as the number of alloy elements increases. This contradicts the major premise of HEAs--that increased configurational entropy increases the stability of disordered solid solution phases. As the number of elements increases, the configurational entropy rises slowly while the probability of at least one pair of elements favouring formation of intermetallic compounds increases more rapidly, explaining this apparent contradiction.

| S-EPMC4366518 | biostudies-literature

Expanded dataset of mechanical properties and observed phases of multi-principal element alloys.

Project description:This data article presents a compilation of mechanical properties of 630 multi-principal element alloys (MPEAs). Built upon recently published MPEA databases, this article includes updated records from previous reviews (with minor error corrections) along with new data from articles that were published since 2019. The extracted properties include reported composition, processing method, microstructure, density, hardness, yield strength, ultimate tensile strength (or maximum compression strength), elongation (or maximum compression strain), and Young's modulus. Additionally, descriptors (e.g. grain size) not included in previous reviews were also extracted for articles that reported them. The database is hosted and continually updated on an open data platform, Citrination. To promote interpretation, some data are graphically presented.

| S-EPMC7722748 | biostudies-literature

Strengthening in multi-principal element alloys with local-chemical-order roughened dislocation pathways.

Project description:High-entropy and medium-entropy alloys are presumed to have a configurational entropy as high as that of an ideally mixed solid solution (SS) of multiple elements in near-equal proportions. However, enthalpic interactions inevitably render such chemically disordered SSs rare and metastable, except at very high temperatures. Here we highlight the wide variety of local chemical ordering (LCO) that sets these concentrated SSs apart from traditional solvent-solute ones. Using atomistic simulations, we reveal that the LCO of the multi-principal-element NiCoCr SS changes with alloy processing conditions, producing a wide range of generalized planar fault energies. We show that the LCO heightens the ruggedness of the energy landscape and raises activation barriers governing dislocation activities. This influences the selection of dislocation pathways in slip, faulting, and twinning, and increases the lattice friction to dislocation motion via a nanoscale segment detrapping mechanism. In contrast, severe plastic deformation reduces the LCO towards random SS.

| S-EPMC6687833 | biostudies-literature

Direct-Contact Cytotoxicity Evaluation of CoCrFeNi-Based Multi-Principal Element Alloys.

Project description:Transition metal multi-principal element alloys (MPEAs) are novel alloys that may offer enhanced surface and mechanical properties compared with commercial metallic alloys. However, their biocompatibility has not been investigated. In this study, three CoCrFeNi-based MPEAs were fabricated, and the in vitro cytotoxicity was evaluated in direct contact with fibroblasts for 168 h. The cell viability and cell number were assessed at 24, 96, and 168 h using LIVE/DEAD assay and alamarBlue assay, respectively. All MPEA sample wells had a high percentage of viable cells at each time point. The two quaternary MPEAs demonstrated a similar cell response to stainless steel control with the alamarBlue assay, while the quinary MPEA with Mn had a lower cell number after 168 h. Fibroblasts cultured with the MPEA samples demonstrated a consistent elongated morphology, while those cultured with the Ni control samples demonstrated changes in cell morphology after 24 h. No significant surface corrosion was observed on the MPEAs or stainless steel samples following the cell culture, while the Ni control samples had extensive corrosion. The cell growth and viability results demonstrate the cytocompatibility of the MPEAs. The biocompatibility of MPEAs should be investigated further to determine if MPEAs may be utilized in orthopedic implants and other biomedical applications.

| S-EPMC6306902 | biostudies-other

An explainable artificial intelligence-enabled electrocardiogram analysis model for the classification of reduced left ventricular function

Project description:Abstract Aims The black box nature of artificial intelligence (AI) hinders the development of interpretable AI models that are applicable in clinical practice. We aimed to develop an AI model for classifying patients of reduced left ventricular ejection fraction (LVEF) from 12-lead electrocardiograms (ECG) with the decision-interpretability. Methods and results We acquired paired ECG and echocardiography datasets from the central and co-operative institutions. For the central institution dataset, a random forest model was trained to identify patients with reduced LVEF among 29 907 ECGs. Shapley additive explanations were applied to 7196 ECGs. To extract the model’s decision criteria, the calculated Shapley additive explanations values were clustered for 192 non-paced rhythm patients in which reduced LVEF was predicted. Although the extracted criteria were different for each cluster, these criteria generally comprised a combination of six ECG findings: negative T-wave inversion in I/V5–6 leads, low voltage in I/II/V4–6 leads, Q wave in V3–6 leads, ventricular activation time prolongation in I/V5–6 leads, S-wave prolongation in V2–3 leads, and corrected QT interval prolongation. Similarly, for the co-operative institution dataset, the extracted criteria comprised a combination of the same six ECG findings. Furthermore, the accuracy of seven cardiologists’ ECG readings improved significantly after watching a video explaining the interpretation of these criteria (before, 62.9% ± 3.9% vs. after, 73.9% ± 2.4%; P = 0.02). Conclusion We visually interpreted the model’s decision criteria to evaluate its validity, thereby developing a model that provided the decision-interpretability required for clinical application. Graphical Abstract Graphical Abstract

| S-EPMC10232279 | biostudies-literature

Supervised Machine Learning Based Multi-Task Artificial Intelligence Classification of Retinopathies.

Project description:Artificial intelligence (AI) classification holds promise as a novel and affordable screening tool for clinical management of ocular diseases. Rural and underserved areas, which suffer from lack of access to experienced ophthalmologists may particularly benefit from this technology. Quantitative optical coherence tomography angiography (OCTA) imaging provides excellent capability to identify subtle vascular distortions, which are useful for classifying retinovascular diseases. However, application of AI for differentiation and classification of multiple eye diseases is not yet established. In this study, we demonstrate supervised machine learning based multi-task OCTA classification. We sought 1) to differentiate normal from diseased ocular conditions, 2) to differentiate different ocular disease conditions from each other, and 3) to stage the severity of each ocular condition. Quantitative OCTA features, including blood vessel tortuosity (BVT), blood vascular caliber (BVC), vessel perimeter index (VPI), blood vessel density (BVD), foveal avascular zone (FAZ) area (FAZ-A), and FAZ contour irregularity (FAZ-CI) were fully automatically extracted from the OCTA images. A stepwise backward elimination approach was employed to identify sensitive OCTA features and optimal-feature-combinations for the multi-task classification. For proof-of-concept demonstration, diabetic retinopathy (DR) and sickle cell retinopathy (SCR) were used to validate the supervised machine leaning classifier. The presented AI classification methodology is applicable and can be readily extended to other ocular diseases, holding promise to enable a mass-screening platform for clinical deployment and telemedicine.

| S-EPMC6617139 | biostudies-literature

Leveraging explainable artificial intelligence to optimize clinical decision support.

Project description:ObjectiveTo develop and evaluate a data-driven process to generate suggestions for improving alert criteria using explainable artificial intelligence (XAI) approaches.MethodsWe extracted data on alerts generated from January 1, 2019 to December 31, 2020, at Vanderbilt University Medical Center. We developed machine learning models to predict user responses to alerts. We applied XAI techniques to generate global explanations and local explanations. We evaluated the generated suggestions by comparing with alert's historical change logs and stakeholder interviews. Suggestions that either matched (or partially matched) changes already made to the alert or were considered clinically correct were classified as helpful.ResultsThe final dataset included 2 991 823 firings with 2689 features. Among the 5 machine learning models, the LightGBM model achieved the highest Area under the ROC Curve: 0.919 [0.918, 0.920]. We identified 96 helpful suggestions. A total of 278 807 firings (9.3%) could have been eliminated. Some of the suggestions also revealed workflow and education issues.ConclusionWe developed a data-driven process to generate suggestions for improving alert criteria using XAI techniques. Our approach could identify improvements regarding clinical decision support (CDS) that might be overlooked or delayed in manual reviews. It also unveils a secondary purpose for the XAI: to improve quality by discovering scenarios where CDS alerts are not accepted due to workflow, education, or staffing issues.

| S-EPMC10990514 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data