Minor Errors Research Articles

Preventing Future Harm: Identifying the Drivers of an Unsafe Discharge to Improve Safety on an Inpatient Oncology Service.

Cancer Morbidity, Mortality, and Improvement Rounds is a series of articles intended to explore the unique safety risks experienced by oncology patients through the lens of quality improvement, systems and human factors engineering, and cognitive psychology. For purposes of clarity, each case focuses on a single theme, although, as is true for all medical incidents, there are almost always multiple, overlapping, contributing factors. The quality improvement paradigm used here, which focuses on root cause analyses and opportunities to improve care delivery systems, was previously outlined in this journal.This article describes the care of a young patient with aggressive breast cancer, declining performance status, and multiple hospital admissions who died shortly after being discharged home without essential medications or an adequate plan for follow-up. The patient's death due to her malignancy was unavoidable, but she had inadequate resources before her death, leading to avoidable suffering. This outcome resulted from a series of minor errors attributable to inadequate handoffs, challenges establishing realistic goals of care, and hierarchy within and between medical teams that resulted in major lapses at the time of discharge. We explore these issues and discuss how this case led to the establishment of programs designed to empower health care providers and increase engagement of outpatient oncologists at critical points of patients' disease courses.

Adaptive finite-time fault-tolerant control for the full-state-constrained robotic manipulator with novel given performance

Most robot manipulators usually operate under different nonlinearities, such as state constraints, time delays, and actuator input saturation faults. This paper proposes an adaptive finite-time fault-tolerant controller for the full-state-constrained robotic manipulator with novel prescribed performance and time-varying delays. Firstly, a novel prescribed performance function consisting of hyperbolic tangent and hyperbolic cotangent functions is constructed to the full-state performance constraints of the robotic manipulator. Such a design can circumvent the demands for accurate initial conditions of the state variables and guarantee the convergence of the state errors in a prescribed time. Then, based on the finite-time principle, a finite-time command filter and a compensation mechanism with fractional-power terms are used to bypass the “explosion of complexity” and further compensate for the filter errors within a finite time. Moreover, a proper Lyapunov–Krasovskii functional is devised within the controller design to compensate for the time-varying delays. And the radial basis function neural networks are used to estimate the other nonlinearities including actuator saturation faults, and external perturbations. Finally, simulation results exhibit that the controller designed in this paper has a faster convergence speed and minor state errors.

A prospective study evaluating the effect of a ‘Diagnostic Stewardship Care-Bundle’ for automated blood culture diagnostics

We prospectively implemented a diagnostic stewardship care-bundle checklist, 'Sepsis-48 DSB', with the aim of reducing intervening duration of key steps of automated blood culture diagnostics (aBCD). Sepsis-48 DSB was implemented for automated blood culture bottles (BCBs) received from adult intensive care units (AICUs) during the intervention period (P2; July 2020-June 2021) and intervening durations were compared with those during the retrospective, pre-intervention period (P1; March-June 2020). During both periods, provisional blood culture reports (pBCR) were issued wherein direct microbial identification (dID) was performed in BCBs with Gram-negatives by directly inoculating conventional biochemical tests and direct antimicrobial susceptibility testing (dAST) using EUCAST RAST method. The results were compared with the standard of care (SoC) method (i.e. full incubation followed by identification and AST by VITEKⓇ-2 Compact). During P2, significant reductions in loading time (LT) [median: 63.5 vs. 32 minutes, P < 0.001], time to dID+dAST performance (TTD) [186 vs. 115 minutes, P=0.0018] and an increase in compliance to bundle targets [LT ≤45: 44% vs. 66%, P=0.006 and TTD ≤120: 34% vs. 51.7%, P=0.03] were observed. Using dID+dAST method, results were read 694 minutes earlier than SoC method. Of 176 pBCR, 165 (94%) were concordant with SoC in microbial identification of species. Categorical agreement for any drug-bug combination was 92.7% (1079/1164) and corresponding major, very major, and minor error rates were 8.8% (19/216), 4.9% (45/921), and 1.8% (21/1164), respectively. The 'diagnostic stewardship care-bundle' strategy was successfully implemented with considerable diagnostic accuracy leading to significant reductions in duration of targeted steps of aBCD.

A Simple Correction for Misspecification in Trend-Cycle Decompositions with an Application to Estimating r*

We propose a simple correction for misspecification in trend-cycle decompositions when the stochastic trend is assumed to be a random walk process but the estimated trend displays some serial correlation in first differences. Possible sources of misspecification that would otherwise be hard to detect and correct for include a small amount of measurement error, omitted variables, or minor approximation errors in model dynamics when estimating trend. Our proposed correction is conducted via application of a univariate Beveridge-Nelson decomposition to the preliminary estimated trend and we show with Monte Carlo analysis that our approach can work as well as if the original model used to estimate trend were correctly specified. We demonstrate the empirical relevance of the correction in an application to estimating r* as the trend of a risk-free short-term real interest rate. We find that our corrected estimate of r* is considerably smoother than the preliminary estimate from a multivariate Beveridge-Nelson decomposition based on a vector error correction model, consistent with the presence of at least a small amount of measurement error in some of the variables included in the multivariate model.

The Management Business Hospitality Students' Competence in Using Past Tense

In English, past tense is one of main tenses which is used in daily life. However, mastering it is not a simple matter. This study aims to find out students past tense mastery competence of the second-semester students of Management Business Hospitality of Triatma Mulya University before they get English Intermediate Course which mainly discuss past activities. Their past tense competence can be assessed by identifying the present and the number of errors which made by the students. The data was gathered by asking them to write down five sentences of their past activities. The subject was a class of second semester students of Management Business Hospitality in total of 21 students. The analysis was conducted by applying Ellis’ error categories of omission, misordering, and misinformation on each sentence of the students. Each sentence made by the students was analyzed to find out the present of each error category. The finding showed that the students had an insufficient competence in using past tense, in which, the major error was in form of misinformation error where the students tended to use present form instead of past form in retelling their past activities. The omission and misordering errors were the minor errors and not as significant as the misinformation error. Keywords: Past Tense Mastery, Competence, Omission, Misordering, Misinformation.

How inadequate heat treatment or complete lack thereof can cause component failures

Abstract This paper is a compilation of failure analysis case studies exploring the subject of inadequate heat treatment. As with other papers in this series, the presented failure cases are rather simple and may appear trivial to the experienced failure analyst. The authors can guarantee however, that minor heat treatment errors are committed easily and have a considerable damage potential which may entail heavy financial losses. Therefore, cases of inadequate heat treatment or a complete lack of necessary heat treatment belong by all means in the column Failure Analysis. The metallurgical subject of these failure cases are low-alloy hardenable steels without exception. Common heat treatment processes such as induction hardening, case hardening, nitriding as well as through-hardening and tempering will be touched upon.

Sentiment Analysis of the 2024 Presidential Candidates Using SMOTE and Long Short Term Memory

Numerous political leaders participate in elections since they are a crucial component of the political process. Since electability is an issue, steps are taken to make political candidates running in general elections more electable. The media, including internet news media, has emerged as one of the key strategies for raising electability. Reader comments can be analyzed for sentiment to provide an evaluation of political figures. However, because the comments contain unstructured content, particularly in Indonesian text, it is difficult to interpret the sentiments of different comments in online news media. In this research, an analysis of public sentiment towards the 2024 presidential candidates will be carried out which is expressed through the Twitter social network. There are several stages to carry out sentiment analysis, including the stages of data collection, data preprocessing, balancing the distribution of the number of datasets, and sentiment classification using the LSTM method with word2vec feature representation. The results of this study show that the LSTM method combined with SMOTE due to the limited amount of data is able to produce a fairly good LSTM model with an average accuracy of 89.42% and a loss value of 0.24, the ideal scenario is when the accuracy is high and the loss is minimal, in which case the LSTM model only exhibits minor errors on a subset of the data.

Comparison of Fuzzy Time Series Markov Chain and Fuzzy Time Series Lee in North Sumatra Import Value Forecasting

North Sumatra is a province that carries out import activities in other provinces to complement the shortage of goods in North Sumatra. Every month based on data from the Central Bureau of Statistics (BPS) of North Sumatra, the import value of North Sumatra constantly fluctuates. So a method is needed to show the increase or decrease in the value of North Sumatra in the next period. The method is forecasting, where forecasting is an activity that predicts something in the future, intending to get information in the next period as a decision or decision in the future. Many forecasting methods can be used, but this study uses fuzzy time series Markov Chain and fuzzy time series Lee methods. These two methods aim to obtain the best forecasting method based on the minor mean absolute percentage error (MAPE) and mean square error (MSE). In this study, the data is on the value of imports in North Sumatra taken from the Central Statistics Agency (BPS) of North Sumatra. The test results on forecasting the import value of North Sumatra show that the fuzzy time series Markov Chain is better than the Fuzzy Time series Lee based on the smallest MAPE and MSE values. The MAPE fuzzy time series Markov Chain value is 7.7467%, and the MSE value is 176,748,587. Meanwhile, Lee's fuzzy time series has a MAPE of 10.014% and an MSE value of 2,387,874,804.

Department Wide Validation in Digital Pathology—Experience from an Academic Teaching Hospital Using the UK Royal College of Pathologists’ Guidance

Aim: we describe our experience of validating departmental pathologists for digital pathology reporting, based on the UK Royal College of Pathologists (RCPath) “Best Practice Recommendations for Implementing Digital Pathology (DP),” at a large academic teaching hospital that scans 100% of its surgical workload. We focus on Stage 2 of validation (prospective experience) prior to full validation sign-off. Methods and results: twenty histopathologists completed Stage 1 of the validation process and subsequently completed Stage 2 validation, prospectively reporting a total of 3777 cases covering eight specialities. All cases were initially viewed on digital whole slide images (WSI) with relevant parameters checked on glass slides, and discordances were reconciled before the case was signed out. Pathologists kept an electronic log of the cases, the preferred reporting modality used, and their experiences. At the end of each validation, a summary was compiled and reviewed with a mentor. This was submitted to the DP Steering Group who assessed the scope of cases and experience before sign-off for full validation. A total of 1.3% (49/3777) of the cases had a discordance between WSI and glass slides. A total of 61% (30/49) of the discordances were categorised as a minor error in a supplementary parameter without clinical impact. The most common reasons for diagnostic discordances across specialities included identification and grading of dysplasia, assessment of tumour invasion, identification of small prognostic or diagnostic objects, interpretation of immunohistochemistry/special stains, and mitotic count assessment. Pathologists showed similar mean diagnostic confidences (on Likert scale from 0 to 7) with a mean of 6.8 on digital and 6.9 on glass slide reporting. Conclusion: we describe one of the first real-world experiences of a department-wide effort to implement, validate, and roll out digital pathology reporting by applying the RCPath Recommendations for Implementing DP. We have shown a very low rate of discordance between WSI and glass slides.

The historical rationale for operating on cranial fissures.

Cranial fissures are not an indication for surgical intervention. It should be emphasised that the term fissure refers to linear skull fractures as defined in MESH. However, it was the universal term for this injuryin the literature which forms the basis of this paper. Nonetheless, for over two millennia, their management was a major reason for opening the skull. The reasons for this deserve analysis, in particular taking into account the available technology and conceptual background. The texts of significant surgical practitioners from Hippocrates to the eighteenth century were examined and analyzed. The need for fissure surgery was based on Hippocrates' teaching. It was considered that extravasated blood would suppurate, and extracranial suppuration could leak inwards through a fracture. Trepanation to facilitate pus drainage and cleansing was considered vital. Avoiding surgical damage to the dura was also emphasized with a preference for operating only when the dura had separated from the cranium. The enlightenment with an increasing reliance on personal observation rather than the teachings of received authority enabled the accumulation of a more rational basis for treatment concerned with the effects of injury on brain function. This culminated in the teachings of Percivall Pott, who despite some minor errors, provided the framework on which modern treatments would develop. Examination of the surgical management of cranial trauma from Hippocrates to the eighteenth century shows that cranial fissures were judged to be of great importance and required active treatment. This treatment was not aimed at improving the healing of the fracture but at avoiding deadly intracranial infection. It is worth noting that this sort of treatment persisted for over two millennia while modern management has only been practiced for just over a century. Who can say how it will change in the next hundred years.

Pharmacokinetic Analysis of Enhancement-Constrained Acceleration (ECA) reconstruction-based high temporal resolution breast DCE-MRI.

The high spatial and temporal resolution of dynamic contrast-enhanced MRI (DCE-MRI) can improve the diagnostic accuracy of breast cancer screening in patients who have dense breasts or are at high risk of breast cancer. However, the spatiotemporal resolution of DCE-MRI is limited by technical issues in clinical practice. Our earlier work demonstrated the use of image reconstruction with enhancement-constrained acceleration (ECA) to increase temporal resolution. ECA exploits the correlation in k-space between successive image acquisitions. Because of this correlation, and due to the very sparse enhancement at early times after contrast media injection, we can reconstruct images from highly under-sampled k-space data. Our previous results showed that ECA reconstruction at 0.25 seconds per image (4 Hz) can estimate bolus arrival time (BAT) and initial enhancement slope (iSlope) more accurately than a standard inverse fast Fourier transform (IFFT) when k-space data is sampled following a Cartesian based sampling trajectory with adequate signal-to-noise ratio (SNR). In this follow-up study, we investigated the effect of different Cartesian based sampling trajectories, SNRs and acceleration rates on the performance of ECA reconstruction in estimating contrast media kinetics in lesions (BAT, iSlope and Ktrans) and in arteries (Peak signal intensity of first pass, time to peak, and BAT). We further validated ECA reconstruction with a flow phantom experiment. Our results show that ECA reconstruction of k-space data acquired with 'Under-sampling with Repeated Advancing Phase' (UnWRAP) trajectories with an acceleration factor of 14, and temporal resolution of 0.5 s/image and high SNR (SNR ≥ 30 dB, noise standard deviation (std) < 3%) ensures minor errors (5% or 1 s error) in lesion kinetics. Medium SNR (SNR ≥ 20 dB, noise std ≤ 10%) was needed to accurately measure arterial enhancement kinetics. Our results also suggest that accelerated temporal resolution with ECA with 0.5 s/image is practical.

Hybrid BO-XGBoost and BO-RF Models for the Strength Prediction of Self-Compacting Mortars with Parametric Analysis.

Self-compacting mortar (SCM) has superior workability and long-term durable performance compared to traditional mortar. The strength of SCM, including both its compressive and flexural strengths, is a crucial property that is determined by appropriate curing conditions and mix design parameters. In the context of materials science, predicting the strength of SCM is challenging because of multiple influencing factors. This study employed machine learning techniques to establish SCM strength prediction models. Based on ten different input parameters, the strength of SCM specimens were predicted using two different types of hybrid machine learning (HML) models, namely Extreme Gradient Boosting (XGBoost) and the Random Forest (RF) algorithm. HML models were trained and tested by experimental data from 320 test specimens. In addition, the Bayesian optimization method was utilized to fine tune the hyperparameters of the employed algorithms, and cross-validation was employed to partition the database into multiple folds for a more thorough exploration of the hyperparameter space while providing a more accurate assessment of the model's predictive power. The results show that both HML models can successfully predict the SCM strength values with high accuracy, and the Bo-XGB model demonstrated higher accuracy (R2 = 0.96 for training and R2 = 0.91 for testing phases) for predicting flexural strength with low error. In terms of compressive strength prediction, the employed BO-RF model performed very well, with R2 = 0.96 for train and R2 = 0.88 testing stages with minor errors. Moreover, the SHAP algorithm, permutation importance and leave-one-out importance score were used for sensitivity analysis to explain the prediction process and interpret the governing input variable parameters of the proposed HML models. Finally, the outcomes of this study might be applied to guide the future mix design of SCM specimens.

Learning to Fake It: Limited Responses and Fabricated References Provided by ChatGPT for Medical Questions

ObjectiveTo evaluate the quality of the answers and the references provided by ChatGPT for medical questions. Patients and MethodsThree researchers asked ChatGPT 20 medical questions and prompted it to provide the corresponding references. The responses were evaluated for the quality of content by medical experts using a verbal numeric scale going from 0% to 100%. These experts were the corresponding authors of the 20 articles from where the medical questions were derived. We planned to evaluate 3 references per response for their pertinence, but this was amended on the basis of preliminary results showing that most references provided by ChatGPT were fabricated. This experimental observational study was conducted in February 2023. ResultsChatGPT provided responses varying between 53 and 244 words long and reported 2 to 7 references per answer. Seventeen of the 20 invited raters provided feedback. The raters reported limited quality of the responses, with a median score of 60% (first and third quartiles: 50% and 85%, respectively). In addition, they identified major (n=5) and minor (n=7) factual errors among the 17 evaluated responses. Of the 59 references evaluated, 41 (69%) were fabricated, although they appeared real. Most fabricated citations used names of authors with previous relevant publications, a title that seemed pertinent and a credible journal format. ConclusionWhen asked multiple medical questions, ChatGPT provided answers of limited quality for scientific publication. More importantly, ChatGPT provided deceptively real references. Users of ChatGPT should pay particular attention to the references provided before integration into medical manuscripts.

Reference accuracy of primary studies published in peer-reviewed scholarly journals: A scoping review

Objective. The objective of this scoping review was to identify key characteristics of primary research studies in peer-reviewed journals about reference accuracy. Characteristics of studies include the publication year, field of study, journal name and publication year of verified references, number of references verified, reference elements examined, definition of major, intermediate, and minor errors, whether punctuation or typographical errors were counted, overall error rate, major, intermediate, and minor error rates, and most common error type. Introduction. Reference accuracy has been studied across several decades and remains a persistent issue in peer-reviewed publications. Reference accuracy is typically reported as an error rate that represents the proportion of references with at least one error. Inclusion criteria for this scoping review included primary studies published in peer-reviewed journals that verified references in articles. Methods. Library, Information Science and Technology Abstracts (LISTA), Medline via EBSCOhost, and Web of Science were searched with final searches conducted in all three databases on November 26, 2022. No grey literature sources were searched given the focus of the project on peer-reviewed scholarly journals. Results. A total of 105 studies were included. The overall error rate across all studies was 32.7%. The error rates within specific fields of study were relatively similar. There is a lack of clarity about whether studies counted punctuation or typographical errors. The most common error was related to author names. Conclusions. There is a lack of studies to understand the most effective means to increase reference accuracy that are feasible to implement on a wide scale. Future research is warranted to understand how best to improve reference accuracy across fields of study.

Effectively fusing clinical knowledge and AI knowledge for reliable lung nodule diagnosis

Clinicians typically use semantic features to judge the malignant status of nodules, while artificial intelligence systems (AI) tend to extract unknown features to diagnose nodules. The former relies on clinical knowledge, while the latter explores AI knowledge. Although many studies indicate that fusing clinical and AI knowledge can help computer-aided diagnosis (CAD) systems improve diagnostic accuracy and gain clinician approval, how to effectively fuse them is still an open question. This paper proposes a simple and effective pipeline (abbreviated as CKAK), which fuses clinical and AI knowledge at both feature and decision levels for accurate lung nodule malignancy classification and semantic attributes characterization. The feature-level fusion can retain rich information in high-dimensional features and improve the model’s accuracy; the decision-level fusion can provide some interpretability for the model’s decision-making process, which is expected in clinical applications. Specifically, the proposed CKAK consists of two sequential stages: (i) the initial prediction stage (IPS); and (ii) the prediction refine stage (PRS). The IPS predicts eight radiologist-interpreted semantic attributes and an initial malignancy diagnosis in parallel. Then, these results are fed to the subsequent PRS to refine the diagnosis further by fully fusing them at feature and decision levels. Besides, to enhance the ability of feature learning, we propose a novel scale-aware feature extraction block (SAFE). It integrates multi-scale contextual features with a lightweight Transformer rather than adding or concatenating them roughly. Extensive experiments at the LIDC-IDRI data set show that the proposed CKAK can achieve superior benign-malignant classification accuracy with minor radiologist-interpreted semantic scores error, meeting the need for a reliable CAD system.

Strategies for a Large Vocabulary Learning Based on Sensorimotor Experiences Referencing the American Television Series Community

The purpose of this paper is to suggest a strategy to enhance vocabulary learning through a sensory-motor experience. A case study was conducted involving four college students who were all non-English majors and had intermediate TOEIC scores. The study emphasized the role of the brain. The material used was from season 1, episode 1 of the American television series &lt;i&gt;Community&lt;/i&gt; (Russo &amp; Russo, 2009). During the study, the four students participated in one instruction session, did three test activities assessing attention and saliency, collocation, memorization, and had an oral interview. In the attention and saliency test, the results revealed that three of the four participants were successful. In the collocation test, three participants were excellent, and one participant was fair. In memorization of an entire dialogue, Participant A was perfect and the other three participants were very good, despite some minor errors. In the oral interview, three participants were positive about using this new method, and one was critical. This participant preferred the traditional vocabulary learning method of matching form-meanings with vocabulary lists. The participants all agreed that this method was innovative and fun, but they all indicated that the instruction was too complicated and suggested that it should be adjusted to make it more understandable.

The advance of neural networks generalization performance

A big mystery in deep learning is the promising generalization performance generated by massive neural networks. While over-parameterization increases the tendency of overfitting in other machine learning models, neural networks seem to magically overcome this hurdle and achieve minor test errors in various tasks. Researchers are motivated to resolve this enigma through a variety of aspects and methods, both theoretically and empirically. This paper aims to comprehensively review the explanations for the generalization power of deep networks. Firstly, the review compares various types of generalization bounds under PAC-Bayes analysis and non-PAC-Bayesian settings. Then, works of regularizers, both explicit (e.g., dropout) and implicit (e.g., batch normalization), and algorithms-caused regularizations are reviewed in this work. Some researchers also explore networks generalization ability from other perspectives, and this review talks about works that investigate the relationship between images and generalization performance. Additionally, works of adversarial examples are included in this review, since adversarial attacks have challenged networks power to generalize well and have become an important field in understanding deep learning. By collecting works from different viewpoints, this paper finally discusses some possible directions in the future.

A pose estimation method of space non-cooperative target based on ORBFPFH SLAM

In this paper, to improve the pose measurement accuracy of the Time-of-Flight (ToF) camera for space non-cooperative targets, a pose estimation method based on ORBFPFH Simultaneous Localization and Mapping (SLAM) with effective integration of strength and depth measurement information is proposed. The primary process of the method is as follows: First, a unique ORBFPFH Bag of Words (BoW) model for space targets is trained based on the ToF image dataset of spacecraft; Secondly, the pose of the non-cooperative space target is tracked based on the ORBFPFH feature and optimized using the pose graph; Then, based on the ORBFPFH BoW model, loop closure is detected to reduce the cumulative error. Finally, the proposed method is tested on the ToF image dataset: compared with the advanced ORB-SLAM2 algorithm, the proposed method has a minor translation error and rotation error on the test data, with a mean translation error less than 0.144 m and mean rotation error less than 0.642°. The test results show that the proposed method can improve the pose estimation accuracy of space non-cooperative targets, achieve a better 3D point cloud reconstruction effect, and provide technical support for space applications such as rendezvous and docking of non-cooperative spacecraft. © 2001 Elsevier Science. All rights reserved

Discovering Similarity Inclusion Dependencies

Inclusion dependencies (INDs) are a well-known type of data dependency, specifying that the values of one column are contained in those of another column. INDs can be used for various purposes, such as foreign-key candidate selection or join partner discovery. The traditional notion of INDs is based on clean data, where the dependencies hold without exceptions. Unfortunately, data often contain errors, preventing otherwise valid INDs from being discovered. A typical response to this problem is to relax the dependency definition using a similarity measure to account for minor data errors, such as typos or different formatting. While this relaxation is known for functional dependencies, for inclusion dependencies no such relaxation has been defined. We formally introduce similarity inclusion dependencies, which relax the inclusion by demanding the existence only of sufficiently similar values. Similarity inclusion dependencies can fulfill traditional IND use cases, such as foreign-key candidate discovery, even in the presence of dirty data. We present Sawfish, the first algorithm to discover all similarity inclusion dependencies in a given dataset efficiently. Our algorithm combines approaches for the discovery of traditional INDs and string similarity joins with a novel sliding-window approach and lazy candidate validation. Our experimental evaluation shows that Sawfish can outperform a baseline by a factor of up to 6.5.

Using Ant Colony Optimization as a Method for Selecting Features to Improve the Accuracy of Measuring the Thickness of Scale in an Intelligent Control System

The scaling of oil pipelines over time leads to issues including diminished flow rates, wasted energy, and decreased efficiency. To take appropriate action promptly and avoid the aforementioned issues, it is crucial to determine the precise value of the scale within the pipe. Non-invasive gamma attenuation systems are one of the most accurate detection methods. To accomplish this goal, the Monte Carlo N Particle (MCNP) algorithm was used to simulate a scale thickness measurement system, which included two sodium iodide detectors, a dual-energy gamma source (241 Am and 133 Ba radioisotopes), and a test pipe. Water, gas, and oil were all used to mimic a three-phase flow in the test pipe, with the volume percentages ranging from 10% to 80%. Moreover, a scale ranging in thickness from 0 to 3 cm was inserted into the pipe, gamma rays were shone on the pipe, and on the opposite side of the pipe, photon intensity was measured by detectors. There were 252 simulations run. Fifteen time and frequency characteristics were derived from the signals collected by the detectors. The ant colony optimisation (ACO)-based approach is used to pick the ideal inputs from among the extracted characteristics for determining the thickness of the scale within the pipe. This technique led to the introduction of thirteen features that represented the ideal combination. The features introduced by ACO were introduced as inputs to a multi-layer perceptron (MLP) neural network to predict the scale thickness inside the oil pipe in centimetres. The maximum error found in calculating scale thickness was 0.017 as RMSE, which is a minor error compared to earlier studies. The accuracy of the present study in detecting scale thickness has been greatly improved by using the ACO to choose the optimal features.