scholarly journals Machine learning analysis of pregnancy data enables early identification of a subpopulation of newborns with ASD

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hugues Caly ◽  
Hamed Rabiei ◽  
Perrine Coste-Mazeau ◽  
Sebastien Hantz ◽  
Sophie Alain ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Behavioral Interventions ◽  
Learning Algorithm ◽  
Statistical Tests ◽  
False Positive Rate ◽  
Supervised Machine Learning ◽  
Fetal Head ◽  
Positive Rate ◽  
History Of

AbstractTo identify newborns at risk of developing ASD and to detect ASD biomarkers early after birth, we compared retrospectively ultrasound and biological measurements of babies diagnosed later with ASD or neurotypical (NT) that are collected routinely during pregnancy and birth. We used a supervised machine learning algorithm with a cross-validation technique to classify NT and ASD babies and performed various statistical tests. With a minimization of the false positive rate, 96% of NT and 41% of ASD babies were identified with a positive predictive value of 77%. We identified the following biomarkers related to ASD: sex, maternal familial history of auto-immune diseases, maternal immunization to CMV, IgG CMV level, timing of fetal rotation on head, femur length in the 3rd trimester, white blood cell count in the 3rd trimester, fetal heart rate during labor, newborn feeding and temperature difference between birth and one day after. Furthermore, statistical models revealed that a subpopulation of 38% of babies at risk of ASD had significantly larger fetal head circumference than age-matched NT ones, suggesting an in utero origin of the reported bigger brains of toddlers with ASD. Our results suggest that pregnancy follow-up measurements might provide an early prognosis of ASD enabling pre-symptomatic behavioral interventions to attenuate efficiently ASD developmental sequels.

scholarly journals Pregnancy data enable identification of relevant biomarkers and a partial prognosis of autism at birth

2020 ◽  
Author(s):  
Hugues Caly ◽  
Hamed Rabiei ◽  
Perrine Coste-Mazeau ◽  
Sebastien Hantz ◽  
Sophie Alain ◽  
...  
Keyword(s):  
Behavioral Interventions ◽  
Statistical Tests ◽  
False Positive Rate ◽  
Familial Risk ◽  
Autism Spectrum ◽  
Gradient Boosting ◽  
Decision Tree Classification ◽  
Positive Rate ◽  
History Of

AbstractAttempts to extract early biomarkers and expedite detection of Autism Spectrum Disorder (ASD) have been centered on postnatal measures of babies at familial risk. Here, we suggest that it might be possible to do these tasks already at birth relying on ultrasound and biological measurements routinely collected from pregnant mothers and fetuses during gestation and birth. We performed a gradient boosting decision tree classification analysis in parallel with statistical tests on a population of babies with typical development or later diagnosed with ASD. By focusing on minimization of the false positive rate, the cross-validated specificity of the classifier reached to 96% with a sensitivity of 41% and a positive predictive value of 77%. Extracted biomarkers included sex, maternal familial history of auto-immune diseases, maternal immunization to CMV, IgG CMV level, timing of fetal rotation on head, femoral length in the 3rd trimester, white cells in the 3rd trimester, fetal heart rate during labour, newborn feeding and newborn’s temperature difference between birth and one day after. Statistical models revealed that 38% of babies later diagnosed with ASD had significantly larger fetal cephalic perimeter than age matched neurotypical babies, suggesting an in-utero origin of the bigger brains of toddlers with ASD. Results pave the way to use pregnancy follow-up measurements to provide an early prognosis of ASD and implement pre-symptomatic behavioral interventions to attenuate efficiently ASD developmental sequels.

scholarly journals A novel machine learning algorithm has the potential to reduce by 1/3 the quantity of ILR episodes needing review

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
A Rosier ◽  
E Crespin ◽  
A Lazarus ◽  
G Laurent ◽  
A Menet ◽  
...  
Keyword(s):  
Machine Learning ◽  
False Positive ◽  
Learning Algorithm ◽  
False Positive Rate ◽  
Machine Learning Algorithm ◽  
The Novel ◽  
Funding Sources ◽  
High Workload ◽  
Positive Rate ◽  
The Impact

Abstract Background Implantable Loop Recorders (ILRs) are increasingly used and generate a high workload for timely adjudication of ECG recordings. In particular, the excessive false positive rate leads to a significant review burden. Purpose A novel machine learning algorithm was developed to reclassify ILR episodes in order to decrease by 80% the False Positive rate while maintaining 99% sensitivity. This study aims to evaluate the impact of this algorithm to reduce the number of abnormal episodes reported in Medtronic ILRs. Methods Among 20 European centers, all Medtronic ILR patients were enrolled during the 2nd semester of 2020. Using a remote monitoring platform, every ILR transmitted episode was collected and anonymised. For every ILR detected episode with a transmitted ECG, the new algorithm reclassified it applying the same labels as the ILR (asystole, brady, AT/AF, VT, artifact, normal). We measured the number of episodes identified as false positive and reclassified as normal by the algorithm, and their proportion among all episodes. Results In 370 patients, ILRs recorded 3755 episodes including 305 patient-triggered and 629 with no ECG transmitted. 2821 episodes were analyzed by the novel algorithm, which reclassified 1227 episodes as normal rhythm. These reclassified episodes accounted for 43% of analyzed episodes and 32.6% of all episodes recorded. Conclusion A novel machine learning algorithm significantly reduces the quantity of episodes flagged as abnormal and typically reviewed by healthcare professionals. FUNDunding Acknowledgement Type of funding sources: None. Figure 1. ILR episodes analysis

scholarly journals LC-MS Peak Assignment Based on Unanimous Selection by Six Machine Learning Algorithms

2021 ◽  
Author(s):  
Hiroaki Ito ◽  
Takashi Matsui ◽  
Ryo Konno ◽  
Makoto Itakura ◽  
Yoshio Kodera
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
False Positive Rate ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Weak Signals ◽  
Accuracy And Precision ◽  
Peak Assignment ◽  
Positive Rate ◽  
Assignment Strategy

Abstract Recent Mass spectrometry (MS)-based techniques enable deep proteome coverage with relative quantitative analysis, resulting in increased identification of very weak signals accompanied by increased data size of liquid chromatography (LC)–MS/MS spectra. However, the identification of weak signals using an assignment strategy with poorer performance resulted in imperfect quantification with misidentification of peaks and ratio distortions. Manually annotating a large number of signals within a very large dataset is not a realistic approach. In this study, therefore, we utilized machine learning algorithms to successfully extract a higher number of peptide peaks with high accuracy and precision. Our strategy evaluated each peak identified using six different algorithms; peptide peaks identified by all six algorithms (i.e., unanimously selected) were subsequently assigned as true peaks, which resulted in a reduction in the false-positive rate. Hence, exact and highly quantitative peptide peaks were obtained, providing better performance than obtained applying the conventional criteria or using a single machine learning algorithm.

scholarly journals Prevention of Crypto-Ransomware Using a Pre-Encryption Detection Algorithm

Computers ◽  
2019 ◽  
Vol 8 (4) ◽  
pp. 79 ◽  
Author(s):  
S. Kok ◽  
Azween Abdullah ◽  
NZ Jhanjhi ◽  
Mahadevan Supramaniam
Keyword(s):  
Machine Learning ◽  
Phase I ◽  
Phase Ii ◽  
Learning Algorithm ◽  
False Positive Rate ◽  
Application Programming Interface ◽  
Detection Algorithm ◽  
Positive Rate ◽  
New Type ◽  
Two Phases

Ransomware is a relatively new type of intrusion attack, and is made with the objective of extorting a ransom from its victim. There are several types of ransomware attacks, but the present paper focuses only upon the crypto-ransomware, because it makes data unrecoverable once the victim’s files have been encrypted. Therefore, in this research, it was proposed that machine learning is used to detect crypto-ransomware before it starts its encryption function, or at the pre-encryption stage. Successful detection at this stage is crucial to enable the attack to be stopped from achieving its objective. Once the victim was aware of the presence of crypto-ransomware, valuable data and files can be backed up to another location, and then an attempt can be made to clean the ransomware with minimum risk. Therefore we proposed a pre-encryption detection algorithm (PEDA) that consisted of two phases. In, PEDA-Phase-I, a Windows application programming interface (API) generated by a suspicious program would be captured and analyzed using the learning algorithm (LA). The LA can determine whether the suspicious program was a crypto-ransomware or not, through API pattern recognition. This approach was used to ensure the most comprehensive detection of both known and unknown crypto-ransomware, but it may have a high false positive rate (FPR). If the prediction was a crypto-ransomware, PEDA would generate a signature of the suspicious program, and store it in the signature repository, which was in Phase-II. In PEDA-Phase-II, the signature repository allows the detection of crypto-ransomware at a much earlier stage, which was at the pre-execution stage through the signature matching method. This method can only detect known crypto-ransomware, and although very rigid, it was accurate and fast. The two phases in PEDA formed two layers of early detection for crypto-ransomware to ensure zero files lost to the user. However in this research, we focused upon Phase-I, which was the LA. Based on our results, the LA had the lowest FPR of 1.56% compared to Naive Bayes (NB), Random Forest (RF), Ensemble (NB and RF) and EldeRan (a machine learning approach to analyze and classify ransomware). Low FPR indicates that LA has a low probability of predicting goodware wrongly.

scholarly journals LC–MS peak assignment based on unanimous selection by six machine learning algorithms

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hiroaki Ito ◽  
Takashi Matsui ◽  
Ryo Konno ◽  
Makoto Itakura ◽  
Yoshio Kodera
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
False Positive Rate ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Weak Signals ◽  
Accuracy And Precision ◽  
Positive Rate ◽  
Assignment Strategy ◽  
Performance Results

AbstractRecent mass spectrometry (MS)-based techniques enable deep proteome coverage with relative quantitative analysis, resulting in increased identification of very weak signals accompanied by increased data size of liquid chromatography (LC)–MS/MS spectra. However, the identification of weak signals using an assignment strategy with poorer performance results in imperfect quantification with misidentification of peaks and ratio distortions. Manually annotating a large number of signals within a very large dataset is not a realistic approach. In this study, therefore, we utilized machine learning algorithms to successfully extract a higher number of peptide peaks with high accuracy and precision. Our strategy evaluated each peak identified using six different algorithms; peptide peaks identified by all six algorithms (i.e., unanimously selected) were subsequently assigned as true peaks, which resulted in a reduction in the false-positive rate. Hence, exact and highly quantitative peptide peaks were obtained, providing better performance than obtained applying the conventional criteria or using a single machine learning algorithm.

scholarly journals Comparison of malware detection techniques using machine learning algorithm

2019 ◽  
Vol 16 (1) ◽  
pp. 435 ◽  
Author(s):  
Nur Syuhada Selamat ◽  
Fakariah Hani Mohd Ali
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
False Positive Rate ◽  
Malware Detection ◽  
Virus Detection ◽  
Detection Accuracy ◽  
Decision Tree Algorithm ◽  
Security Threat ◽  
Detection Techniques ◽  
Positive Rate

<p>Currently, the volume of malware grows faster each year and poses a thoughtful global security threat. The number of malware developed increases as computers became interconnected, at an alarming rate in the 1990s. This scenario resulted the increment of malware. It also caused many protections are built to fight the malware. Unfortunately, the current technology is no longer effective to handle more advanced malware. Malware authors have created them to become more difficult to be evaded from anti-virus detection. In the current research, Machine Learning (ML) algorithm techniques became more popular to the researchers to analyze malware detection. In this paper, researchers proposed a defense system which uses three ML algorithm techniques comparison and select them based on the high accuracy malware detection. The result indicates that Decision Tree algorithm is the best detection accuracy compares to others classifier with 99% and 0.021% False Positive Rate (FPR) on a relatively small dataset.</p>

scholarly journals Prediction of severe COVID-19 infection at the time of testing: A machine learning approach

2021 ◽  
Author(s):  
Faraz Khoshbaktian ◽  
Ardian Lagman ◽  
Dionne M Aleman ◽  
Randy Giffen ◽  
Proton Rahman
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
False Positive Rate ◽  
Class Imbalance ◽  
Severe Infection ◽  
True Positive Rate ◽  
Support Vector ◽  
Limited Information ◽  
Rt Pcr ◽  
Positive Rate

Early and effective detection of severe infection cases during a pandemic can significantly help patient prognosis and resource allocation. We develop a machine learning framework for detecting severe COVID-19 cases at the time of RT-PCR testing. We retrospectively studied 988 patients from a small Canadian province that tested positive for SARS-CoV-2 where 42 (4%) cases were at-risk (i.e., resulted in hospitalization, admission to ICU, or death), and 8 (<1%) cases resulted in death. The limited information available at the time of RT-PCR testing included age, comorbidities, and patients' reported symptoms, totaling 27 features. Due to the severe class imbalance and small dataset size, we formulated the problem of detecting severe COVID as anomaly detection and applied three models: one-class support vector machine (OCSVM), weight-adjusted XGBoost, and weight-adjusted AdaBoost. The OCSVM was the best performing model for detecting the deceased cases with an average 95% true positive rate (TPR) and 27.2% false positive rate (FPR). Meanwhile, the XGBoost provided the best performance for detecting the at-risk cases with an average 96.2% TPR and 19% FPR. In addition, we developed a novel extension to SHAP interpretability to explain the outputs from the models. In agreement with conventional knowledge, we found that comorbidities were influential in predicting severity, however, we also found that symptoms were generally more influential, noting that machine learning combines all available data and is not a single-variate statistical analysis.

scholarly journals Predictive Modelling of Employee Turnover in Indian IT Industry Using Machine Learning Techniques

2019 ◽  
Vol 23 (1) ◽  
pp. 12-21 ◽  
Author(s):  
Shikha N. Khera ◽  
Divya
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Confusion Matrix ◽  
Predictive Modelling ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
It Industry ◽  
Knowledge Based ◽  
Employee Attrition

Information technology (IT) industry in India has been facing a systemic issue of high attrition in the past few years, resulting in monetary and knowledge-based loses to the companies. The aim of this research is to develop a model to predict employee attrition and provide the organizations opportunities to address any issue and improve retention. Predictive model was developed based on supervised machine learning algorithm, support vector machine (SVM). Archival employee data (consisting of 22 input features) were collected from Human Resource databases of three IT companies in India, including their employment status (response variable) at the time of collection. Accuracy results from the confusion matrix for the SVM model showed that the model has an accuracy of 85 per cent. Also, results show that the model performs better in predicting who will leave the firm as compared to predicting who will not leave the company.

scholarly journals Identification of abnormal tribological regimes using a microphone and semi-supervised machine-learning algorithm

Friction ◽  
2021 ◽  
Author(s):  
Vigneashwara Pandiyan ◽  
Josef Prost ◽  
Georg Vorlaufer ◽  
Markus Varga ◽  
Kilian Wasmer
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Industrial Applications ◽  
Supervised Machine Learning ◽  
Normal Operation ◽  
Promising Alternative ◽  
Wear And Tear ◽  
Validation Procedure ◽  
And Performance

AbstractFunctional surfaces in relative contact and motion are prone to wear and tear, resulting in loss of efficiency and performance of the workpieces/machines. Wear occurs in the form of adhesion, abrasion, scuffing, galling, and scoring between contacts. However, the rate of the wear phenomenon depends primarily on the physical properties and the surrounding environment. Monitoring the integrity of surfaces by offline inspections leads to significant wasted machine time. A potential alternate option to offline inspection currently practiced in industries is the analysis of sensors signatures capable of capturing the wear state and correlating it with the wear phenomenon, followed by in situ classification using a state-of-the-art machine learning (ML) algorithm. Though this technique is better than offline inspection, it possesses inherent disadvantages for training the ML models. Ideally, supervised training of ML models requires the datasets considered for the classification to be of equal weightage to avoid biasing. The collection of such a dataset is very cumbersome and expensive in practice, as in real industrial applications, the malfunction period is minimal compared to normal operation. Furthermore, classification models would not classify new wear phenomena from the normal regime if they are unfamiliar. As a promising alternative, in this work, we propose a methodology able to differentiate the abnormal regimes, i.e., wear phenomenon regimes, from the normal regime. This is carried out by familiarizing the ML algorithms only with the distribution of the acoustic emission (AE) signals captured using a microphone related to the normal regime. As a result, the ML algorithms would be able to detect whether some overlaps exist with the learnt distributions when a new, unseen signal arrives. To achieve this goal, a generative convolutional neural network (CNN) architecture based on variational auto encoder (VAE) is built and trained. During the validation procedure of the proposed CNN architectures, we were capable of identifying acoustics signals corresponding to the normal and abnormal wear regime with an accuracy of 97% and 80%. Hence, our approach shows very promising results for in situ and real-time condition monitoring or even wear prediction in tribological applications.

Sign in / Sign up

Export Citation Format

Share Document