Assessment Of Machine Learning Techniques Research Articles

Remote sensing detection of plastic-mulched farmland using a temporal approach in machine learning: case study in tomato crops.

The increasing use of plastics in rural environments has led to concerns about agricultural plastic waste (APW). However, the plasticulture information gap hinders waste management planning and may lead to plastic residue leakage into the environment with consequent microplastic formation. The location and estimated quantity of the APW are crucial for territorial planning and public policies regarding land use and waste management. Agri-plastic remote detection has attracted increased attention but requires a consensus approach, particularly for mapping plastic-mulched farmlands (PMFs) scattered across vast areas. This article tests whether a streamlined time-series approach minimizes PMF confusion with the background using less processing. Based on the literature, we performed a vast assessment of machine learning techniques and investigated the importance of features in mapping tomato PMF. We evaluated pixel-based and object-based classifications in harmonized Sentinel-2 level-2A images, added plastic indices, and compared six classifiers. The best result showed an overall accuracy of 99.7% through pixel-based using the multilayer perceptron (MLP) classifier. The 3-time series with a 30-day composite exhibited increased accuracy, a decrease in background confusion, and was a viable alternative for overcoming the impact of cloud cover on images at certain times of the year in our study area, which leads to a potentially reliable methodology for APW mapping for future studies. To our knowledge, the presented PMF map is the first for Latin America. This represents a first step toward promoting the circularity of all agricultural plastic in the region, minimizing the impacts of degradation on the environment.

Assessment of Machine Learning Techniques for Simulating Reacting Flow: From Plasma-Assisted Ignition to Turbulent Flame Propagation

Combustion involves the study of multiphysics phenomena that includes fluid and chemical kinetics, chemical reactions and complex nonlinear processes across various time and space scales. Accurate simulation of combustion is essential for designing energy conversion systems. Nonetheless, due to its multiscale, multiphysics nature, simulating these systems at full resolution is typically difficult. The massive and complex data generated from experiments and simulations, particularly in turbulent combustion, presents both a challenge and a research opportunity for advancing combustion studies. Machine learning facilitates data-driven techniques to manage the substantial amount of combustion data that is either obtained through experiments or simulations, and thereby can find the hidden patterns underlying these data. Alternatively, machine learning models can be useful to make predictions with comparable accuracy to existing models, while reducing computational costs significantly. In this era of big data, machine learning is rapidly evolving, offering promising opportunities to explore its integration with combustion research. This work provides an in-depth overview of machine learning applications in turbulent combustion modeling and presents the application of machine learning models: Decision Trees (DT) and Random Forests (RF), for the spatio-temporal prediction of plasma-assisted ignition kernels, based on the initial degree of ionization, with model validations against DNS data. The results demonstrate that properly trained machine learning models can accurately predict the spatio-temporal ignition kernel profile based on the initial energy deposition and distribution.

Artificial intelligence for screening and early diagnosis of pancreatic neoplasms in the context of centralization of the laboratory service in the region.

Objective. Determination of the optimal machine learning model for the creation of software for screening and early diagnosis of pancreatic neoplasms in the context of centralization of the laboratory service in the region. Material and Methods. The clinical material was based on 1254 patients who were examined in the centralized laboratory of the Volgograd Consultative and Diagnostic Polyclinic No. 2. Of these, 139 were subsequently operated on at the Volgograd Regional Clinical Oncology Dispensary for pancreatic malignancies. In 65 (46.7 %) cases, distal pancreatic resection was performed, and in 74 (53.3 %) cases, pancreaticoduodenectomy was performed. In 28 (20.1 %) cases, at the time of tumor detection, patients did not have clinical symptoms. Statistical processing of the data was carried out using the Python programming language. Five different classifiers were used for machine learning. Results. In the course of factor analysis, 11 parameters were selected from 62 laboratory blood parameters, the dynamics of changes in which should be specifically assessed at the stages of screening and early diagnosis of pancreatic neoplasms. A comparative assessment of machine learning techniques showed that the best option for creating the appropriate software was Hist Gradient Boosting (diagnostic accuracy 0.909, sensitivity 0.642, specificity 0.965, negative predictability 0.928, positive predictability 0.794, F1 0.828, logistic regression loss function 0.352, area under the ROC curve 0.89). Conclusion. The creation of software based on the selected algorithm will make it possible to clarify the real effectiveness of machine learning on a larger population of patients with pancreatic neoplasms.

Thorough Assessment of Machine Learning Techniques for Predicting Protein-Nucleic Acid Binding Hot Spots

Background: Proteins and nucleic acids are vital biomolecules that contribute significantly to biological life. The precise and efficient identification of hot spots at protein-nucleic acid interfaces is crucial for guiding drug development, advancing protein engineering, and exploring the underlying molecular recognition mechanisms. As experimental methods like alanine scanning mutagenesis prove to be time-consuming and expensive, a growing number of machine learning techniques are being employed to predict hot spots. However, the existing approach is distinguished by a lack of uniform standards, a scarcity of data, and a wide range of attributes. Currently, there is no comprehensive overview or evaluation of this field. As a result, providing a full overview and review is extremely helpful. Methods: In this study, we present an overview of cutting-edge machine learning approaches utilized for hot spot prediction in protein-nucleic acid complexes. Additionally, we outline the feature categories currently in use, derived from relevant biological data sources, and assess conventional feature selection methods based on 600 extracted features. Simultaneously, we create two new benchmark datasets, PDHS87 and PRHS48, and develop distinct binary classification models based on these datasets to evaluate the advantages and disadvantages of various machine-learning techniques. Results: Prediction of protein-nucleic acid interaction hotspots is a challenging task. The study demonstrates that structural neighborhood features play a crucial role in identifying hot spots. The prediction performance can be improved by choosing effective feature selection methods and machine learning methods. Among the existing prediction methods, XGBPRH has the best performance. Conclusion: It is crucial to continue studying hot spot theories, discover new and effective features, add accurate experimental data, and utilize DNA/RNA information. Semi-supervised learning, transfer learning, and ensemble learning can optimize predictive ability. Combining computational docking with machine learning methods can potentially further improve predictive performance.

Performance Assessment of Machine Learning Techniques for Gully Erosion Mapping in South-East Nigeria

Soil erosion is a serious environmental hazard affecting southeast Nigeria. The rate of erosion has continued to increase with devastating impact and has led to land degradation (gullies). To assess the socio-economic and environmental implications of gully erosion and to develop management plans to deal with them, quantitative and qualitative data on soil erosion rates at regional scales are needed. Hence, this study aimed at investigating the spatial and temporal variations of gully erosion impacted areas of South East Nigeria using machine learning techniques to develop a suitable approach for accurately modelling gully erosion impact in South East, Nigeria. Its objectives are to: acquire, process, and perform object-based gully mapping analysis with Kompsat-3 imagery of South East Nigeria, Nigeria using three machine learning algorithms (Linear discriminant analysis, Support Vector Machine, and Artificial Neural Network); compare the performance of the three selected machine learning algorithms using statistical techniques and determine the best suited for gully mapping within the study area; determine the pattern and trend of Gully Erosion in South East, Nigeria between 2010 and 2020, using the best-suited machine learning algorithm; and predict the future gully development pattern for the next 10 years. The methodology involved the acquisition and use of KOMPSAT-3 imagery, identification of gully erosion impacted areas, and topographic maps. Image preprocessing, development of classification scheme, object-based image analysis, trend analysis, and pattern of gully development and expansion. Accuracy assessment and gully development prediction to 2030 as data analysis. The results showed consistent identification of eight class features, including waterbody, dense vegetation, agricultural land, bare ground, built-up area, sand, savannah, and gully erosion. The performance evaluation of the three techniques revealed promising outcomes. LDA achieved an accuracy of 0.759, while SVM demonstrated a higher accuracy of 0.853 and balanced sensitivity and specificity. ANN showed good performance with an accuracy of 0.790. Based on its superior accuracy and balanced performance, SVM was selected for mapping the spatial trend of gully erosion in the study area.

Machine learning algorithms for privacy preserving in vehicular ad hoc network

Machine learning (ML) will improve the outcomes through the use of methods that categorize the information into the predetermined set. This work is to present an estimation and assessment of machine learning techniques for achieving privacy preservation in vehicular ad hoc networks (VANETs). This method generates two distinct group keys for prime and secondary users. Road side units (RSUs) are deployed to broadcast one group key from the trusted authority (TA) to the primary users, and secondary users are utilized to transmit the other group key. The main aim of this network is developed to avoid vulnerable attacks and to enhance the privacy of this network, Naïve Bayesian classifier (BC), support vector machine (SVM), K-nearest neighbor (KNN), artificial neural networks (ANN), Bayesian network (BN) methods are utilized in correlation with the proposed deep neural networks (DNN) with the black widow optimization (BWO) for protection preserving. These learning characterization procedures are assessed concerning delay, network lifetime, throughput, delivery ratio, and drop and this proposed calculation (DNN-BWO) shows improved results than the current methodologies.

Advances and critical assessment of machine learning techniques for prediction of docking scores

AbstractHere we present three distinct machine learning (ML) approaches (TensorFlow, XGBoost, and SchNetPack) for docking score prediction. AutoDock Vina is used to evaluate the inhibitory potential of ZINC15 in‐vivo and in‐vitro‐only sets towards the SARS‐CoV‐2 main protease. The in‐vivo set (59 884 compounds) is used for ML training (max. 80%), validation (5%), and testing (15%). The in‐vitro‐only set (174 014 compounds) is used for the evaluation of prediction capability of the trained ML models. Contributions to the prediction error are analyzed with respect to compounds' charge, number of atoms, and expected inhibitory potential (docking score). Methods for the prediction error estimation of new compounds are considered, yet critically rejected. The ML input weighted with respect to the desired property (i.e., low docking score) in the machine learning models shows to be a promising option to improve the ML performance. Proposed models provide significant reduction in number of intriguing compounds that need to be investigated.

Assessment of Machine Learning Techniques and Traffic Flow: A Qualitative and Quantitative Analysis

Traffic flow analysis is an interesting study topic in transportation studies. A better understanding of traffic flow is essential for more effective traffic reduction methods. Because managing traffic flow in cities is getting more complicated, we need more methodical ways to deal with these problems. Machine learning techniques have been suggested as a possible solution because they can process great amounts of data and give insights that can be used to help make decisions about how to manage traffic. The main objective of this research is to conduct a comprehensive examination of the quantitative and qualitative aspects of utilizing machine learning techniques in the management of traffic flow. Using the Web of Science (WOS) platform, documents from January 2007 to April 2023 were assessed. The study found that traffic flow management has been using machine learning techniques more and more over the past few years. This study shows the different approaches and methods that were used, as well as the results and limits of these methods. The results recommend that machine learning can be a useful tool for managing traffic flow in cities, but further investigation is warranted to gain a complete comprehension of both the advantages and disadvantages of the subject under scrutiny.

Assessment of machine learning techniques for prediction of integrated water vapor using meteorological data

Weather and Climatological studies are very important in assessing atmospheric conditions like storms and cyclones. Integrated water vapor (IWV) is an important greenhouse gas in the atmosphere responsible for the Earth's radiative balance. Global Positioning System (GPS) observations have been used for monitoring the IWV variability. The IWV estimations are carried out using ground-based GPS observations at Hyderabad (17.4°N, 78.46°E), India using GAMIT software. GAMIT is GPS analysis software developed by MIT, USA. It takes input as GPS observation data containing pseudo ranges, navigation data containing ephemeris, clock errors, g-files with orbital information, and meteorological data like pressure, temperature, and relative humidity to calculate IWV. However, estimating IWV for forecasting applications is impossible with a GPS system. This paper introduces a methodology to predict IWV during normal days and severe cyclonic events using machine learning (ML) techniques. Rational quadratic Gaussian process regression (RQ-GPR) and neural network (NN) algorithms are considered for identifying suitable ML prediction algorithms over tropical conditions. Meteorological surface data like Pressure, Temperature, and relative humidity are given as input to the machine learning models. The IWV values computed from GPS are compared with the model's predicted values. RQ-GPR model is showing good accuracy with the IWV values computed from GPS against the NN model. The correlation coefficient (ρ) achieved for RQ-GPR is 0.93, and 0.86 is obtained for the NN model.
 The RMSE (Root Mean Square Error) of the predicted IWV value with RQ-GPR is better than the NN model. We have obtained mean square error (MSE) and mean absolute error (MAE) as 18.146 kg/m2 and 3.0762 kg/m2 for RQ-GPR and 27.509 kg/m2 and 3.9102 kg/m2 for the NN model which is showing RQ-GPR is a suitable model for forecasting applications. The HUDHUD cyclonic event that occurred in October 2014 is considered for testing the proposed ML algorithms. RQ-GPR model has better results in the Prediction of IWV than the NN model. The RMSE value obtained is 2.837 kg/m2 for RQ-GPR and 3.327 kg/m2 obtained from the NN model. The results indicate that the RQ-GPR model has more accuracy than the other IWV prediction models. The prediction results are helpful for meteorology, weather, and climatology studies and useful to improve the accuracy of the regional numerical weather prediction models.

Assessment of Machine Learning Techniques for Oil Rig Classification in C-Band SAR Images

This article aims at performing maritime target classification in SAR images using machine learning (ML) and deep learning (DL) techniques. In particular, the targets of interest are oil platforms and ships located in the Campos Basin, Brazil. Two convolutional neural networks (CNNs), VGG-16 and VGG-19, were used for attribute extraction. The logistic regression (LR), random forest (RF), support vector machine (SVM), k-nearest neighbours (kNN), decision tree (DT), naive Bayes (NB), neural networks (NET), and AdaBoost (ADBST) schemes were considered for classification. The target classification methods were evaluated using polarimetric images obtained from the C-band synthetic aperture radar (SAR) system Sentinel-1. Classifiers are assessed by the accuracy indicator. The LR, SVM, NET, and stacking results indicate better performance, with accuracy ranging from 84.1% to 85.5%. The Kruskal–Wallis test shows a significant difference with the tested classifier, indicating that some classifiers present different accuracy results. The optimizations provide results with more significant accuracy gains, making them competitive with those shown in the literature. There is no exact combination of methods for SAR image classification that will always guarantee the best accuracy. The optimizations performed in this article were for the specific data set of the Campos Basin, and results may change depending on the data set format and the number of images.

Predicting the abrasion loss of open-graded friction course mixes with EAF steel slag aggregates using machine learning algorithms

This study presents a comparative assessment of machine learning techniques for modeling the abrasion loss (AL) of open-graded friction course (OGFC) mixes. The proposed approach is Orthogonal Matching Pursuit (OMP), Huber Regressor (HR), Lasso Lars CV (LLCV), Lars CV (LCV), and Ridge Regressor (RR). To construct and validate the proposed models, a sum of 228 experiments of OGFC mixes with different proportions of natural aggregates and electric arc furnace (EAF) steel slag were performed. Based on the analyses with 4 different combinations of input parameters, the proposed OMP model exhibits the most accurate prediction of AL of OGFC mix in both training and validation phases. Comparison of results of the developed models indicated that the OMP model has the potential to be a new alternative to assist engineers/practitioners in estimating the AL of OGFC mixes. In addition, the effect of % replacement of natural aggregates with electric arc furnace steel slag can also be studied.

Assessment of Machine Learning Techniques in IoT-Based Architecture for the Monitoring and Prediction of COVID-19

From the end of 2019, the world has been facing the threat of COVID-19. It is predicted that, before herd immunity is achieved globally via vaccination, people around the world will have to tackle the COVID-19 pandemic using precautionary steps. This paper suggests a COVID-19 identification and control system that operates in real-time. The proposed system utilizes the Internet of Things (IoT) platform to capture users’ time-sensitive symptom information to detect potential cases of coronaviruses early on, to track the clinical measures adopted by survivors, and to gather and examine appropriate data to verify the existence of the virus. There are five key components in the framework: symptom data collection and uploading (via communication technology), a quarantine/isolation center, an information processing core (using artificial intelligent techniques), cloud computing, and visualization to healthcare doctors. This research utilizes eight machine/deep learning techniques—Neural Network, Decision Table, Support Vector Machine (SVM), Naive Bayes, OneR, K-Nearest Neighbor (K-NN), Dense Neural Network (DNN), and the Long Short-Term Memory technique—to detect coronavirus cases from time-sensitive information. A simulation was performed to verify the eight algorithms, after selecting the relevant symptoms, on real-world COVID-19 data values. The results showed that five of these eight algorithms obtained an accuracy of over 90%. Conclusively, it is shown that real-world symptomatic information would enable these three algorithms to identify potential COVID-19 cases effectively with enhanced accuracy. Additionally, the framework presents responses to treatment for COVID-19 patients.

Empirical Assessment of Machine Learning Techniques for Software Requirements Risk Prediction

Software risk prediction is the most sensitive and crucial activity of Software Development Life Cycle (SDLC). It may lead to the success or failure of a project. The risk should be predicted earlier to make a software project successful. A model is proposed for the prediction of software requirement risks using requirement risk dataset and machine learning techniques. In addition, a comparison is made between multiple classifiers that are K-Nearest Neighbour (KNN), Average One Dependency Estimator (A1DE), Naïve Bayes (NB), Composite Hypercube on Iterated Random Projection (CHIRP), Decision Table (DT), Decision Table/Naïve Bayes Hybrid Classifier (DTNB), Credal Decision Trees (CDT), Cost-Sensitive Decision Forest (CS-Forest), J48 Decision Tree (J48), and Random Forest (RF) achieve the best suited technique for the model according to the nature of dataset. These techniques are evaluated using various evaluation metrics including CCI (correctly Classified Instances), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Absolute Error (RAE), Root Relative Squared Error (RRSE), precision, recall, F-measure, Matthew’s Correlation Coefficient (MCC), Receiver Operating Characteristic Area (ROC area), Precision-Recall Curves area (PRC area), and accuracy. The inclusive outcome of this study shows that in terms of reducing error rates, CDT outperforms other techniques achieving 0.013 for MAE, 0.089 for RMSE, 4.498% for RAE, and 23.741% for RRSE. However, in terms of increasing accuracy, DT, DTNB, and CDT achieve better results.

Brine-Oil Interfacial Tension Modeling: Assessment of Machine Learning Techniques Combined with Molecular Dynamics.

The physical chemistry mechanisms behind the oil-brine interface phenomena are not yet fully clarified. The knowledge of the relation between brine composition and concentration for a given oil may lead to the ionic tuning of the injected solution on geochemical and enhanced oil recovery processes. Thus, it is worth examining the parameters influencing the interfacial properties. In this context, we have combined machine learning (ML) techniques with classical molecular dynamics simulations (MD) to predict oil/brine interfacial tensions (IFT) effectively and compared this process to a linear regression (LR) method. To diversify our data set, we have introduced a new atomistic crude oil model (medium) with 36 different types of hydrocarbon molecules. The MD simulations were performed for mono- and multicomponent (toluene, heptane, Heptol, light, and medium) oil systems interfaced with sulfate and chloride brines with varying cations (Na+, K+, Ca2+, and Mg2+) and salinity concentration. Thus, a consistent IFT data set was built for the ML training and LR fitting at room temperature and pressure conditions, over the feature space considering oil density, oil composition, salinity, and ionic concentrations. On the basis of gradient boosted (GB) algorithms, we have observed that the dominant quantities affecting the IFT are related to the oil attributes and the salinity concentration, and no specific ion dominates the IFT changes. When the obtained LR model was validated against MD and experimental data from the literature, the error varied up to 2% and 9%, respectively, showing a robust and consistent transferability. The combination of MD simulations and ML techniques may provide a fast and cost-effective IFT determination over multiple and complex fluid-fluid and fluid-solid interfaces.

Assessment of Machine Learning Techniques for Gold Price Predictions

Assessment of Machine Learning Techniques for Gold Price Predictions

Assessment of machine-learning techniques in predicting lithofluid facies logs in hydrocarbon wells

Wireline log interpretation is a well-exercised procedure in the oil and gas industry with all its added value from exploration to production stages. It becomes even more important when it is one of only a few available alternatives to compensate for the lack of core samples in a study of lithologic and fluid variations in a well. Yet, as with other purely expert-oriented interpretational techniques, there is always a considerable risk of subjective or technical errors. We have adopted a hybrid approach that links a machine-learning (ML) algorithm to the log interpretation procedure to solve these problems. We have applied this approach to two different hydrocarbon (HC) fields with the aim of predicting the HC-bearing units in the form of lithofluid facies logs at different well locations. The values of these logs are labels of classes that are separated based on their lithologic and fluid content characteristics. After training different MLs on the designed lithofluid facies logs, we chose a bagged-tree algorithm to predict these logs for the target wells due to its superior performance. This algorithm predicted HC units in an accurate interval (above the HC-fluid contact depth), and it showed a very low false discovery rate. The high-accuracy rate, speed of analysis, and its generalization ability, even in data-deficient cases, accentuate why including ML algorithms can improve the understanding of the subsurface at every phase of the exploration and production process. The proposed approach of using ML algorithms, trained and tuned based on the expert’s knowledge of the reservoir, can be modified and applied to future wells in a HC field to significantly minimize the risk of false HC discoveries.

Assessment of Machine Learning Techniques for Monthly Flow Prediction

Monthly flow predictions provide an essential basis for efficient decision-making regarding water resource allocation. In this paper, the performance of different popular data-driven models for monthly flow prediction is assessed to detect the appropriate model. The considered methods include feedforward neural networks (FFNNs), time delay neural networks (TDNNs), radial basis neural networks (RBFNNs), recurrent neural network (RNN), a grasshopper optimization algorithm (GOA)-based support vector machine (SVM) and K-nearest neighbors (KNN) model. For this purpose, the performance of each model is evaluated in terms of several residual metrics using a monthly flow time series for two real case studies with different flow regimes. The results show that the KNN outperforms the different neural network configurations for the first case study, whereas RBFNN model has better performance for the second case study in terms of the correlation coefficient. According to the accuracy of the results, in the first case study with more input features, the KNN model is recommended for short-term predictions and for the second case with a smaller number of input features, but more training observations, the RBFNN model is suitable.

Assessment of machine learning techniques for deterministic and probabilistic intra-hour solar forecasts

Abstract This work compares the performance of machine learning methods (k-nearest-neighbors (kNN) and gradient boosting (GB)) in intra-hour forecasting of global (GHI) and direct normal (DNI) irradiances. The models predict the GHI and DNI and the corresponding prediction intervals. The data used in this work include pyranometer measurements of GHI and DNI and sky images. Point forecasts are evaluated using bulk error metrics while the performance of the probabilistic forecasts are quantified using metrics such as Prediction Interval Coverage Probability (PICP), Prediction Interval Normalized Averaged Width (PINAW) and the Continuous Ranked Probability Score (CRPS). Graphical verification displays like reliability diagram and rank histogram are used to assess the probabilistic forecasts. Results show that the machine learning models achieve significant forecast improvements over the reference model. The reduction in the RMSE translates into forecasting skills ranging between 8% and 24%, and 10% and 30% for the GHI and DNI testing set, respectively. CRPS skill scores of 42% and 62% are obtained respectively for GHI and DNI probabilistic forecasts. Regarding the point forecasts, the GB method performs better than the kNN method when sky image features are included in the model. Conversely, for probabilistic forecasts the kNN exhibits rather good performance.

Assessment of machine-learning techniques on large pathology data sets to address assay redundancy in routine liver function test profiles.

Routine liver function tests (LFTs) are central to serum testing profiles, particularly in community medicine. However there is concern about the redundancy of information provided to requesting clinicians. Large quantities of clinical laboratory data and advances in computational knowledge discovery methods provide opportunities to re-examine the value of individual routine laboratory results that combine for LFT profiles. The machine learning methods recursive partitioning (decision trees) and support vector machines (SVMs) were applied to aggregate clinical chemistry data that included elevated LFT profiles. Response categories for γ-glutamyl transferase (GGT) were established based on whether the patient results were within or above the sex-specific reference interval. Single decision tree and SVMs were applied to test the accuracy of GGT prediction by the highest ranked predictors of GGT response, alkaline phosphatase (ALP) and alanine amino-transaminase (ALT). Through interrogating more than 20,000 individual cases comprising both sexes and all ages, decision trees predicted GGT category at 90% accuracy using only ALP and ALT, with a SVM prediction accuracy of 82.6% after 10-fold training and testing. Bilirubin, lactate dehydrogenase (LD) and albumin did not enhance prediction, or reduced accuracy. Comparison of abnormal (elevated) GGT categories also supported the primacy of ALP and ALT as screening markers, with serum urate and cholesterol also useful. Machine-learning interrogation of massive clinical chemistry data sets demonstrated a strategy to address redundancy in routine LFT screening by identifying ALT and ALP in tandem as able to accurately predict GGT elevation, suggesting that GGT can be removed from routine LFT screening.

Deep assessment of machine learning techniques using patient treatment in acute abdominal pain in children

Learning from patient records may aid knowledge acquisition and decision making. Existing inductive machine learning (ML) systems such us Newld, CN2, C4.5 and AQ15 learn from past case histories using symbolic and/or numeric values. These systems learn symbolic rules (IF… THEN like) which link an antecedent set of clinical factors to a consequent class or decision. This paper compares the learning performance of alternative ML systems with each other and with respect to a novel approach using logic minimization, called LML, to learn from data. Patient cases were taken from the archives of the Paediatric Surgery Clinic of the University Hospital of Crete, Heraklion, Greece. Comparison of ML system performance is based both on classification accuracy and on informal expert assessment of learned knowledge.