ABSTRACT
Spectroscopic techniques generate one-dimensional spectra with distinct peaks and specific widths in the frequency domain. These features act as unique identities for material characteristics. Deep neural networks (DNNs) has recently been considered a powerful tool for automatically categorizing experimental spectra data by supervised classification to evaluate material characteristics. However, most existing work assumes balanced spectral data among various classes in the training data, contrary to actual experiments, where the spectral data is usually imbalanced. The imbalanced training data deteriorates the supervised classification performance, hindering understanding of the phase behavior, specifically, sol-gel transition (gelation) of soft materials and glycomaterials. To address this issue, this paper applies a novel data augmentation method based on a generative adversarial network (GAN) proposed by the authors in their prior work. To demonstrate the effectiveness of the proposed method, the actual imbalanced spectral data from Pluronic F-127 hydrogel and Alpha-Cyclodextrin hydrogel are used to classify the phases of data. Specifically, our approach improves 8.8%, 6.4%, and 6.2% of the performance of the existing data augmentation methods regarding the classifier's F-score, Precision, and Recall on average, respectively. Specifically, our method consists of three DNNs: the generator, discriminator, and classifier. The method generates samples that are not only authentic but emphasize the differentiation between material characteristics to provide balanced training data, improving the classification results. Based on these validated results, we expect the method's broader applications in addressing imbalanced measurement data across diverse domains in materials science and chemical engineering.
ABSTRACT
Stereoselective reactions have played a vital role in the emergence of life, evolution, human biology, and medicine. However, for a long time, most industrial and academic efforts followed a trial-and-error approach for asymmetric synthesis in stereoselective reactions. In addition, most previous studies have been qualitatively focused on the influence of steric and electronic effects on stereoselective reactions. Therefore, quantitatively understanding the stereoselectivity of a given chemical reaction is extremely difficult. As proof of principle, this paper develops a novel composite machine learning method for quantitatively predicting the enantioselectivity representing the degree to which one enantiomer is preferentially produced from the reactions. Specifically, machine learning methods that are widely used in data analytics, including Random Forest, Support Vector Regression, and LASSO, are utilized. In addition, the Bayesian optimization and permutation importance tests are provided for an in-depth understanding of reactions and accurate prediction. Finally, the proposed composite method approximates the key features of the available reactions by using Gaussian mixture models, which provide suitable machine learning methods for new reactions. The case studies using the real stereoselective reactions show that the proposed method is effective and provides a solid foundation for further application to other chemical reactions.
ABSTRACT
BACKGROUND: Decompressive craniectomy (DC) reduces mortality without increasing the risk of very severe disability among patients with life-threatening massive cerebral infarction. However, its efficacy was demonstrated before the era of endovascular thrombectomy trials. It remains uncertain whether DC improves the prognosis of patients with malignant middle cerebral artery (MCA) infarction receiving endovascular therapy. METHODS: We pooled data from two trials (DEVT and RESCUE BT studies in China) and patients with malignant MCA infarction were included to assess outcomes and heterogeneity of DC therapy effect. Patients with herniation were dichotomized into DC and conservative groups according to their treatment strategy. The primary outcome was the rate of mortality at 90 days. Secondary outcomes included disability level at 90 days as measured by the modified Rankin Scale score (mRS) and quality-of-life score. The associations of DC with clinical outcomes were performed using multivariable logistic regression. RESULTS: Of 98 patients with herniation, 37 received DC surgery and 61 received conservative treatment. The median (interquartile range) was 70 (62-76) years and 40.8% of the patients were women. The mortality rate at 90 days was 59.5% in the DC group compared with 85.2% in the conservative group (adjusted odds ratio, 0.31 [95% confidence interval (CI), 0.10-0.94]; P=0.04). There were 21.6% of patients in the DC group and 6.6% in the conservative group who had a mRS score of 4 (moderately severe disability); and 10.8% and 4.9%, respectively, had a score of 5 (severe disability). The quality-of-life score was higher in the DC group (0.00 [0.00-0.14] vs 0.00 [0.00-0.00], P=0.004), but DC treatment was not associated with better quality-of-life score in multivariable analyses (adjusted ß Coefficient, 0.02 [95% CI, -0.08-0.11]; p=0.75). CONCLUSIONS: DC was associated with decreased mortality among patients with malignant MCA infarction who received endovascular therapy. The majority of survivors remained moderately severe disability and required improvement on quality of life. CLINICAL TRIAL REGISTRATION: The DEVT trial: http://www.chictr.org. Identifier, ChiCTR-IOR-17013568. The RESCUE BT trial: URL: http://www.chictr.org. Identifier, ChiCTR-INR-17014167.
Subject(s)
Decompressive Craniectomy , Disability Evaluation , Infarction, Middle Cerebral Artery , Aged , Female , Humans , Male , Middle Aged , China , Decompressive Craniectomy/mortality , Decompressive Craniectomy/adverse effects , Functional Status , Infarction, Middle Cerebral Artery/mortality , Infarction, Middle Cerebral Artery/surgery , Infarction, Middle Cerebral Artery/therapy , Infarction, Middle Cerebral Artery/diagnosis , Infarction, Middle Cerebral Artery/physiopathology , Quality of Life , Randomized Controlled Trials as Topic , Recovery of Function , Risk Assessment , Risk Factors , Time Factors , Treatment OutcomeABSTRACT
The training and testing data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the testing samples are drawn from a distribution that is sufficiently far away from that of the training samples (a.k.a. out-of-distribution (OOD) samples), the trained neural network has a tendency to make high-confidence predictions for these OOD samples. Detection of the OOD samples is critical when training a neural network used for image classification, object detection, etc. It can enhance the classifier's robustness to irrelevant inputs, and improve the system's resilience and security under different forms of attacks. Detection of OOD samples has three main challenges: (i) the proposed OOD detection method should be compatible with various architectures of classifiers (e.g., DenseNet, ResNet) without significantly increasing the model complexity and requirements on computational resources; (ii) the OOD samples may come from multiple distributions, whose class labels are commonly unavailable; (iii) a score function needs to be defined to effectively separate OOD samples from in-distribution (InD) samples. To overcome these challenges, we propose a Wasserstein-based out-of-distribution detection (WOOD) method. The basic idea is to define a Wasserstein-based score that evaluates the dissimilarity between a test sample and the distribution of InD samples. An optimization problem is then formulated and solved based on the proposed score function. The statistical learning bound of the proposed method is investigated to guarantee that the loss value achieved by the empirical optimizer approximates the global optimum. The comparison study results demonstrate that the proposed WOOD consistently outperforms other existing OOD detection methods.
ABSTRACT
False results and time delay are longstanding challenges in biosensing. While classification models and deep learning may provide new opportunities for improving biosensor performance, such as measurement confidence and speed, it remains a challenge to ensure that predictions are explainable and consistent with domain knowledge. Here, we show that consistency of deep learning classification model predictions with domain knowledge in biosensing can be achieved by cost function supervision and enables rapid and accurate biosensing using the biosensor dynamic response. The impact and utility of the methodology were validated by rapid and accurate quantification of microRNA (let-7a) across the nanomolar (nM) to femtomolar (fM) concentration range using the dynamic response of cantilever biosensors. Data augmentation and cost function supervision based on the consistency of model predictions and experimental observations with the theory of surface-based biosensors improved the F1 score, precision, and recall of a recurrent neural network (RNN) classifier by an average of 13.8%. The theory-guided RNN (TGRNN) classifier enabled quantification of target analyte concentration and false results with an average prediction accuracy, precision, and recall of 98.5% using the initial transient or entire dynamic response, which is indicative of high prediction accuracy and low probability of false-negative and false-positive results. Classification scores were used to establish new relationships among biosensor performance characteristics (e.g., measurement confidence) and design parameters (e.g., inputs and hyperparameters of classification models and data acquisition parameters) that may be used for characterizing biosensor performance.
Subject(s)
Biosensing Techniques , Deep Learning , MicroRNAs , Biosensing Techniques/methods , Neural Networks, Computer , AlgorithmsABSTRACT
Here, we provide a new methodology for reducing false results and time delay of biosensors, which are barriers to industrial, healthcare, military, and consumer applications. We show that integrating machine learning with domain knowledge in biosensing can complement and improve the biosensor accuracy and speed relative to the performance achieved by traditional regression analysis of a standard curve based on the biosensor steady-state response. The methodology was validated by rapid and accurate quantification of microRNA across the nanomolar to femtomolar range using the dynamic response of cantilever biosensors. Theory-guided feature engineering improved the performance and efficiency of several classification models relative to the performance achieved using traditional feature engineering methods (TSFRESH). In addition to the entire dynamic response, the technique enabled rapid and accurate quantification of the target analyte concentration and false-positive and false-negative results using the initial transient response, thereby reducing the required data acquisition time (i.e., time delay). We show that model explainability can be achieved by combining theory-guided feature engineering and feature importance analysis. The performance of multiple classifiers using both TSFRESH- and theory-based features from the biosensor's initial transient response was similar to that achieved using the entire dynamic response with data augmentation. We also show that the methodology can guide design of experiments for high-performance biosensing applications, specifically, the selection of data acquisition parameters (e.g., time) based on potential application-dependent performance thresholds. This work provides an example of the opportunities for improving biosensor performance, such as reducing biosensor false results and time delay, using explainable machine learning models supervised by domain knowledge in biosensing.
Subject(s)
Biosensing Techniques , Machine Learning , Biosensing Techniques/methodsABSTRACT
Designing and printing metamaterials with customizable architectures enables the realization of unprecedented mechanical behaviors that transcend those of their constituent materials. These behaviors are recorded in the form of response curves, with stress-strain curves describing their quasi-static footprint. However, existing inverse design approaches are yet matured to capture the full desired behaviors due to challenges stemmed from multiple design objectives, nonlinear behavior, and process-dependent manufacturing errors. Here, we report a rapid inverse design methodology, leveraging generative machine learning and desktop additive manufacturing, which enables the creation of nearly all possible uniaxial compressive stressâstrain curve cases while accounting for process-dependent errors from printing. Results show that mechanical behavior with full tailorability can be achieved with nearly 90% fidelity between target and experimentally measured results. Our approach represents a starting point to inverse design materials that meet prescribed yet complex behaviors and potentially bypasses iterative design-manufacturing cycles.
ABSTRACT
Differential equations are fundamental in modeling numerous physical systems, including thermal, manufacturing, and meteorological systems. Traditionally, numerical methods often approximate the solutions of complex systems modeled by differential equations. With the advent of modern deep learning, Physics-informed Neural Networks (PINNs) are evolving as a new paradigm for solving differential equations with a pseudo-closed form solution. Unlike numerical methods, the PINNs can solve the differential equations mesh-free, integrate the experimental data, and resolve challenging inverse problems. However, one of the limitations of PINNs is the poor training caused by using the activation functions designed typically for purely data-driven problems. This work proposes a scalable tanh-based activation function for PINNs to improve learning the solutions of differential equations. The proposed Self-scalable tanh (Stan) function is smooth, non-saturating, and has a trainable parameter. It can allow an easy flow of gradients and enable systematic scaling of the input-output mapping during training. Various forward problems to solve differential equations and inverse problems to find the parameters of differential equations demonstrate that the Stan activation function can achieve better training and more accurate predictions than the existing activation functions for PINN in the literature.
ABSTRACT
An effective lithium-ion battery (LIB) recycling infrastructure is of great importance to alleviate the concerns over the disposal of waste LIBs and the sustainability of critical elements for producing LIB components. The End-of-life (EOL) LIBs are in various sizes and shapes, which create significant challenges to automate a few unit operations (e.g., disassembly at the cell level) of the recycling process. Meanwhile, hazardous and flammable materials are contained in LIBs, posing great threats to the human exposure. Therefore, it is difficult to dismantle the LIBs safely and efficiently to recover critical materials. Automation has become a competitive solution in manufacturing world, which allows for mass production at outstanding speeds and with great repeatability or quality. It is imperative to develop automatic disassembly solution to effectively disassemble the LIBs while safeguarding human workers against the hazards environment. In this work, we demonstrate an automatic battery disassembly platform enhanced by online sensing and machine learning technologies. The computer vision is used to classify different types of batteries based on their brands and sizes. The real-time temperature data is captured from a thermal camera. A data-driven model is built to predict the cutting temperature pattern and the temperature spike can be mitigated by the close-loop control system. Furthermore, quality control is conducted using a neural network model to detect and mitigate the cutting defects. The integrated disassembly platform can realize the real-time diagnosis and closed-loop control of the cutting process to optimize the cutting quality and improve the safety. Supplementary Information: The online version contains supplementary material available at 10.1007/s10845-022-01936-x.
ABSTRACT
Laser powder bed fusion is a promising technology for local deposition and microstructure control, but it suffers from defects such as delamination and porosity due to the lack of understanding of melt pool dynamics. To study the fundamental behavior of the melt pool, both geometric and thermal sensing with high spatial and temporal resolutions are necessary. This work applies and integrates three advanced sensing technologies: synchrotron X-ray imaging, high-speed IR camera, and high-spatial-resolution IR camera to characterize the evolution of the melt pool shape, keyhole, vapor plume, and thermal evolution in Ti-6Al-4V and 410 stainless steel spot melt cases. Aside from presenting the sensing capability, this paper develops an effective algorithm for high-speed X-ray imaging data to identify melt pool geometries accurately. Preprocessing methods are also implemented for the IR data to estimate the emissivity value and extrapolate the saturated pixels. Quantifications on boundary velocities, melt pool dimensions, thermal gradients, and cooling rates are performed, enabling future comprehensive melt pool dynamics and microstructure analysis. The study discovers a strong correlation between the thermal and X-ray data, demonstrating the feasibility of using relatively cheap IR cameras to predict features that currently can only be captured using costly synchrotron X-ray imaging. Such correlation can be used for future thermal-based melt pool control and model validation.
ABSTRACT
In the face of the increasingly serious rapid depletion of fossil fuels, exploring alternative energy conversion technologies may be a promising choice to alleviate this crisis. Transition metal carbides (TMCs)/carbon composites are considered as prospective electrocatalysts due to their high catalytic activities and structural stability. In this work, we report the simple synthesis of TMCs/N-doping carbon aerogels (TMCs/NCAs, including Fe3C/NCA, Mo3C2/NCA, and Fe3C-Mo2C/NCA) for the oxygen reduction reaction (ORR) using protonated chitosan/metal complex anion-chelated aerogels. Among them, the Fe3C/NCA composite possesses efficient ORR activity (similar to Pt/C), and the Fe3C/NCA-assembled Zn-air battery exhibits high power densities of about 250 mW cm-2. The density functional theory calculation reveals that the presence of graphite-N, pyridine-N, and carbon defects in the carbon framework effectively reduces the free energy of ORR occurring in Fe3C. This work provides a simple and extensible strategy for the preparation of TMCs from chitosan, which is expected to be extended to other metal carbides.
ABSTRACT
Studies on materials affected by large thermal gradients and rapid thermal cycling are an area of increasing interest, driving the need for real time observations of microstructural evoultion under transient thermal conditions. However, current in situ transmission electron microscope (TEM) heating stages introduce uniform temperature distributions across the material during heating experiments. Here, a methodology is described to generate thermal gradients across a TEM specimen by modifying a commercially available MEMS-based heating stage. It was found that a specimen placed next to the metallic heater, over a window, cut by FIB milling, does not disrupt the overall thermal stability of the device. Infrared thermal imaging (IRTI) experiments were performed on unmodified and modified heating devices, to measure thermal gradients across the device. The mean temperature measured within the central viewing area of the unmodified device was 3-5% lower than the setpoint temperature. Using IRTI data, at setpoint temperatures ranging from 900 to 1,300°C, thermal gradients at the edge of the modified window were calculated to be in the range of 0.6 × 106 to 7.0 × 106 °C/m. Additionally, the Ag nanocube sublimation approach was used, to measure the local temperature across a FIB-cut Si lamella at high spatial resolution inside the TEM, and demonstrate "proof of concept" of the modified MEMS device. The thermal gradient across the Si lamella, measured using the latter approach was found to be 6.3 × 106 °C/m, at a setpoint temperature of 1,000°C. Finally, the applicability of this approach and choice of experimental parameters are critically discussed.
ABSTRACT
Here, we present a closed-loop controlled photopolymerization process for fabrication of hydrogels with controlled storage moduli. Hydrogel crosslinking was associated with a significant change in the phase angle of a piezoelectric cantilever sensor and established the timescale of the photopolymerization process. The composition, structure, and mechanical properties of the fabricated hydrogels were characterized using Raman spectroscopy, scanning electron microscopy (SEM), and dynamic mechanical analysis (DMA). We found that the storage moduli of photocured poly(ethylene glycol) dimethacrylate (PEGDMA) and poly(N-isopropylacrylamide) (PNIPAm) hydrogels could be controlled using bang-bang and fuzzy logic controllers. Bang-bang controlled photopolymerization resulted in constant overshoot of the storage modulus setpoint for PEGDMA hydrogels, which was mitigated by setpoint correction and fuzzy logic control. SEM and DMA studies showed that the network structure and storage modulus of PEGDMA hydrogels were dependent on the cure time and temporal profile of UV exposure during photopolymerization. This work provides an advance in pulsed and continuous photopolymerization processes for hydrogel engineering based on closed-loop control that enables reproducible fabrication of hydrogels with controlled mechanical properties.
ABSTRACT
Traditional self-injurious behavior (SIB) management can place compliance demands on the caregiver and have low ecological validity and accuracy. To support an SIB monitoring system for autism spectrum disorder (ASD), we evaluated machine learning methods for detecting and distinguishing diverse SIB types. SIB episodes were captured with body-worn accelerometers from children with ASD and SIB. The highest detection accuracy was found with k-nearest neighbors and support vector machines (up to 99.1% for individuals and 94.6% for grouped participants), and classification efficiency was quite high (offline processing at ~ 0.1 ms/observation). Our results provide an initial step toward creating a continuous and objective smart SIB monitoring system, which could in turn facilitate the future care of a pervasive concern in ASD.
Subject(s)
Autism Spectrum Disorder/classification , Autism Spectrum Disorder/diagnosis , Machine Learning/classification , Self-Injurious Behavior/classification , Self-Injurious Behavior/diagnosis , Adolescent , Autism Spectrum Disorder/psychology , Child , Child, Preschool , Cluster Analysis , Electrocardiography/methods , Female , Humans , Male , Self-Injurious Behavior/psychologyABSTRACT
Physical monitoring systems represent potentially powerful assessment devices to detect and describe occupational physical activities. A promising technology for such use is smart textile systems (STSs). Our goal in this exploratory study was to assess the feasibility and accuracy of using two STSs to classify several manual material handling (MMH) tasks. Specifically, commercially-available 'smart' socks and a custom 'smart' shirt were used individually and in combination. Eleven participants simulated nine separate MMH tasks while wearing the STSs, and task classification accuracy was quantified subsequently using several common models. The shirt and socks, both individually and in combination, could classify the simulated tasks with greater than 97% accuracy. Thus, using STSs appears to have potential utility for discriminating occupational physical tasks in the work environment. Practitioner summary: A smart textile system could classify diverse MMH tasks with high accuracy. This technology may help in developing future ergonomic exposure assessment systems, with the goal of preventing occupational injuries.
Subject(s)
Ergonomics/methods , Monitoring, Physiologic/methods , Task Performance and Analysis , Adolescent , Adult , Computer Simulation , Female , Humans , Male , Occupational Diseases/prevention & control , Occupational Health , Occupational Injuries/prevention & control , Textiles , Work/physiology , Workplace , Young AdultABSTRACT
The temporal and spatial patterns of nanoparticle that ferry both imaging and therapeutic agent in solid tumors is significantly influenced by target tissue movement, low spatial resolution, and inability to accurately define regions of interest (ROI) at certain tissue depths. These combine to limit and define nanoparticle untreated regions in tumors. Utilizing graph and matrix theories, the objective of this project was to develop a novel spectral Fiedler field (SFF) based-computational technology for nanoparticle mapping in tumors. The novelty of SFF lies in the utilization of the changes in the tumor topology from baseline for contrast variation assessment. Data suggest that SFF can enhance the spatiotemporal contrast compared to conventional method by 2-3 folds in tumors. Additionally, the SFF contrast is readily translatable for assessment of tumor drug distribution. Thus, our SFF computational platform has the potential for integration into devices that allow contrast and drug delivery applications.
Subject(s)
Algorithms , Colonic Neoplasms/diagnostic imaging , Contrast Media/chemistry , Diagnostic Imaging , Nanoparticles/chemistry , Animals , Cell Line, Tumor , Colonic Neoplasms/drug therapy , Colonic Neoplasms/pathology , Doxorubicin/pharmacology , Doxorubicin/therapeutic use , Liposomes , Mice , Temperature , UltrasonographyABSTRACT
Antenatal urine of 497 pregnant women was collected in the Department of Gynecology and Obstetrics of a county hospital in Jiaozuo, Henan. The content of the main metabolites of synthetic pyrethroid pesticides in urine were determined. After 1 year, physical development indices of 1-year old infants, such as height, weight, and head and chest circumference, were measured. The neural and mental development of the infants was assessed by the Development Screen Test (DST) scale. We observed that the level of synthetic pyrethroid pesticide exposure was negatively related to the neural and mental development of infants (ß = -0.1527, P < 0.05). Therefore, direct or indirect exposure to synthetic pyrethroid pesticides should be avoided during pregnancy.
Subject(s)
Child Development/drug effects , Developmental Disabilities/chemically induced , Pesticides/toxicity , Prenatal Exposure Delayed Effects/chemically induced , Pyrethrins/toxicity , Adolescent , Adult , China , Female , Humans , Infant , Male , Mental Disorders/chemically induced , Middle Aged , Nervous System/drug effects , Nervous System/growth & development , Nervous System Diseases/chemically induced , Pesticides/urine , Pregnancy , Pyrethrins/urine , Young AdultABSTRACT
OBJECTIVE: The prediction of survival time after organ transplantations and prognosis analysis of different risk groups of transplant patients are not only clinically important but also technically challenging. The current studies, which are mostly linear modeling-based statistical analyses, have focused on small sets of disparate predictive factors where many potentially important variables are neglected in their analyses. Data mining methods, such as machine learning-based approaches, are capable of providing an effective way of overcoming these limitations by utilizing sufficiently large data sets with many predictive factors to identify not only linear associations but also highly complex, non-linear relationships. Therefore, this study is aimed at exploring risk groups of thoracic recipients through machine learning-based methods. METHODS AND MATERIAL: A large, feature-rich, nation-wide thoracic transplantation dataset (obtained from the United Network for Organ Sharing-UNOS) is used to develop predictive models for the survival time estimation. The predictive factors that are most relevant to the survival time identified via, (1) conducting sensitivity analysis on models developed by the machine learning methods, (2) extraction of variables from the published literature, and (3) eliciting variables from the medical experts and other domain specific knowledge bases. A unified set of predictors is then used to develop a Cox regression model and the related prognosis indices. A comparison of clustering algorithm-based and conventional risk grouping techniques is conducted based on the outcome of the Cox regression model in order to identify optimal number of risk groups of thoracic recipients. Finally, the Kaplan-Meier survival analysis is performed to validate the discrimination among the identified various risk groups. RESULTS: The machine learning models performed very effectively in predicting the survival time: the support vector machine model with a radial basis Kernel function produced the best fit with an R(2) value of 0.879, the artificial neural network (multilayer perceptron-MLP-model) came the second with an R(2) value of 0.847, and the M5 algorithm-based regression tree model came last with an R(2) value of 0.785. Following the proposed method, a consolidated set of predictive variables are determined and used to build the Cox survival model. Using the prognosis indices revealed by the Cox survival model along with a k-means clustering algorithm, an optimal number of "three" risk groups is identified. The significance of differences among these risk groups are also validated using the Kaplan-Meier survival analysis. CONCLUSIONS: This study demonstrated that the integrated machine learning method to select the predictor variables is more effective in developing the Cox survival models than the traditional methods commonly found in the literature. The significant distinction among the risk groups of thoracic patients also validates the effectiveness of the methodology proposed herein. We anticipate that this study (and other AI based analytic studies like this one) will lead to more effective analyses of thoracic transplant procedures to better understand the prognosis of thoracic organ recipients. It would potentially lead to new medical and biological advances and more effective allocation policies in the field of organ transplantation.
Subject(s)
Data Mining/methods , Lung Transplantation , Medical Informatics Applications , Databases, Factual , Female , Humans , Kaplan-Meier Estimate , Male , Models, Biological , PrognosisABSTRACT
BACKGROUND: Predicting the survival of heart-lung transplant patients has the potential to play a critical role in understanding and improving the matching procedure between the recipient and graft. Although voluminous data related to the transplantation procedures is being collected and stored, only a small subset of the predictive factors has been used in modeling heart-lung transplantation outcomes. The previous studies have mainly focused on applying statistical techniques to a small set of factors selected by the domain-experts in order to reveal the simple linear relationships between the factors and survival. The collection of methods known as 'data mining' offers significant advantages over conventional statistical techniques in dealing with the latter's limitations such as normality assumption of observations, independence of observations from each other, and linearity of the relationship between the observations and the output measure(s). There are statistical methods that overcome these limitations. Yet, they are computationally more expensive and do not provide fast and flexible solutions as do data mining techniques in large datasets. PURPOSE: The main objective of this study is to improve the prediction of outcomes following combined heart-lung transplantation by proposing an integrated data-mining methodology. METHODS: A large and feature-rich dataset (16,604 cases with 283 variables) is used to (1) develop machine learning based predictive models and (2) extract the most important predictive factors. Then, using three different variable selection methods, namely, (i) machine learning methods driven variables-using decision trees, neural networks, logistic regression, (ii) the literature review-based expert-defined variables, and (iii) common sense-based interaction variables, a consolidated set of factors is generated and used to develop Cox regression models for heart-lung graft survival. RESULTS: The predictive models' performance in terms of 10-fold cross-validation accuracy rates for two multi-imputed datasets ranged from 79% to 86% for neural networks, from 78% to 86% for logistic regression, and from 71% to 79% for decision trees. The results indicate that the proposed integrated data mining methodology using Cox hazard models better predicted the graft survival with different variables than the conventional approaches commonly used in the literature. This result is validated by the comparison of the corresponding Gains charts for our proposed methodology and the literature review based Cox results, and by the comparison of Akaike information criteria (AIC) values received from each. CONCLUSIONS: Data mining-based methodology proposed in this study reveals that there are undiscovered relationships (i.e. interactions of the existing variables) among the survival-related variables, which helps better predict the survival of the heart-lung transplants. It also brings a different set of variables into the scene to be evaluated by the domain-experts and be considered prior to the organ transplantation.