scholarly journals NIMG-68. ACCURATE PATIENT-SPECIFIC MACHINE LEARNING MODELS OF GLIOBLASTOMA INVASION USING TRANSFER LEARNING

2017 ◽  
Vol 19 (suppl_6) ◽  
pp. vi157-vi158 ◽  
Author(s):  
Leland Hu ◽  
Hyunsoo Yoon ◽  
Jennifer Eschbacher ◽  
Leslie Baxter ◽  
Kris Smith ◽  
...  
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
Patient Specific ◽  
Learning Models ◽  
Machine Learning Models

Effect of a Real-Time Risk Score on 30-day Readmission Reduction in Singapore

2021 ◽  
Vol 12 (02) ◽  
pp. 372-382
Author(s):  
Christine Xia Wu ◽  
Ernest Suresh ◽  
Francis Wei Loong Phng ◽  
Kai Pik Tai ◽  
Janthorn Pakdeethai ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Real Time ◽  
Risk Score ◽  
Patient Specific ◽  
Learning Models ◽  
Medicine Department ◽  
High Risk Patients ◽  
Risk Patients ◽  
Machine Learning Models

Abstract Objective To develop a risk score for the real-time prediction of readmissions for patients using patient specific information captured in electronic medical records (EMR) in Singapore to enable the prospective identification of high-risk patients for enrolment in timely interventions. Methods Machine-learning models were built to estimate the probability of a patient being readmitted within 30 days of discharge. EMR of 25,472 patients discharged from the medicine department at Ng Teng Fong General Hospital between January 2016 and December 2016 were extracted retrospectively for training and internal validation of the models. We developed and implemented a real-time 30-day readmission risk score generation in the EMR system, which enabled the flagging of high-risk patients to care providers in the hospital. Based on the daily high-risk patient list, the various interfaces and flow sheets in the EMR were configured according to the information needs of the various stakeholders such as the inpatient medical, nursing, case management, emergency department, and postdischarge care teams. Results Overall, the machine-learning models achieved good performance with area under the receiver operating characteristic ranging from 0.77 to 0.81. The models were used to proactively identify and attend to patients who are at risk of readmission before an actual readmission occurs. This approach successfully reduced the 30-day readmission rate for patients admitted to the medicine department from 11.7% in 2017 to 10.1% in 2019 (p < 0.01) after risk adjustment. Conclusion Machine-learning models can be deployed in the EMR system to provide real-time forecasts for a more comprehensive outlook in the aspects of decision-making and care provision.

Intra-domain and cross-domain transfer learning for time series

2021 ◽  
Author(s):  
Erik Otović ◽  
Marko Njirjak ◽  
Dario Jozinović ◽  
Goran Mauša ◽  
Alberto Michelini ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Transfer Learning ◽  
Time Series Data ◽  
The Other ◽  
Series Data ◽  
Sound Recognition ◽  
Transfer Of Knowledge ◽  
Learning Models ◽  
Machine Learning Models

&lt;p&gt;In this study, we compared the performance of machine learning models trained using transfer learning and those that were trained from scratch - on time series data. Four machine learning models were used for the experiment. Two models were taken from the field of seismology, and the other two are general-purpose models for working with time series data. The accuracy of selected models was systematically observed and analyzed when switching within the same domain of application (seismology), as well as between mutually different domains of application (seismology, speech, medicine, finance). In seismology, we used two databases of local earthquakes (one in counts, and the other with the instrument response removed) and a database of global earthquakes for predicting earthquake magnitude; other datasets targeted classifying spoken words (speech), predicting stock prices (finance) and classifying muscle movement from EMG signals (medicine).&lt;br&gt;In practice, it is very demanding and sometimes impossible to collect datasets of tagged data large enough to successfully train a machine learning model. Therefore, in our experiment, we use reduced data sets of 1,500 and 9,000 data instances to mimic such conditions. Using the same scaled-down datasets, we trained two sets of machine learning models: those that used transfer learning for training and those that were trained from scratch. We compared the performances between pairs of models in order to draw conclusions about the utility of transfer learning. In order to confirm the validity of the obtained results, we repeated the experiments several times and applied statistical tests to confirm the significance of the results. The study shows when, within the set experimental framework, the transfer of knowledge brought improvements in terms of model accuracy and in terms of model convergence rate.&lt;br&gt;&lt;br&gt;Our results show that it is possible to achieve better performance and faster convergence by transferring knowledge from the domain of global earthquakes to the domain of local earthquakes; sometimes also vice versa. However, improvements in seismology can sometimes also be achieved by transferring knowledge from medical and audio domains. The results show that the transfer of knowledge between other domains brought even more significant improvements, compared to those within the field of seismology. For example, it has been shown that models in the field of sound recognition have achieved much better performance compared to classical models and that the domain of sound recognition is very compatible with knowledge from other domains. We came to similar conclusions for the domains of medicine and finance. Ultimately, the paper offers suggestions when transfer learning is useful, and the explanations offered can provide a good starting point for knowledge transfer using time series data.&lt;/p&gt;

The Classification of Skateboarding Tricks by Means of the Integration of Transfer Learning and Machine Learning Models

2020 ◽  
pp. 219-226
Author(s):  
Muhammad Nur Aiman Shapiee ◽  
Muhammad Ar Rahim Ibrahim ◽  
Mohd Azraai Mohd Razman ◽  
Muhammad Amirul Abdullah ◽  
Rabiu Muazu Musa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
Learning Models ◽  
Machine Learning Models

scholarly journals Heart Failure Diagnosis, Readmission, and Mortality Prediction Using Machine Learning and Artificial Intelligence Models

2020 ◽  
Vol 7 (4) ◽  
pp. 212-219 ◽  
Author(s):  
Aixia Guo ◽  
Michael Pasque ◽  
Francis Loh ◽  
Douglas L. Mann ◽  
Philip R. O. Payne
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Outcome Prediction ◽  
Predictive Accuracy ◽  
Imbalanced Data ◽  
Mortality Prediction ◽  
Machine Learning Techniques ◽  
Patient Specific ◽  
Learning Models ◽  
Machine Learning Models

Abstract Purpose of Review One in five people will develop heart failure (HF), and 50% of HF patients die in 5 years. The HF diagnosis, readmission, and mortality prediction are essential to develop personalized prevention and treatment plans. This review summarizes recent findings and approaches of machine learning models for HF diagnostic and outcome prediction using electronic health record (EHR) data. Recent Findings A set of machine learning models have been developed for HF diagnostic and outcome prediction using diverse variables derived from EHR data, including demographic, medical note, laboratory, and image data, and achieved expert-comparable prediction results. Summary Machine learning models can facilitate the identification of HF patients, as well as accurate patient-specific assessment of their risk for readmission and mortality. Additionally, novel machine learning techniques for integration of diverse data and improvement of model predictive accuracy in imbalanced data sets are critical for further development of these promising modeling methodologies.

Predicting High-Flow Nasal Cannula Failure in an ICU Using a Recurrent Neural Network with Transfer Learning and Input Data Perseveration: A Retrospective Analysis (Preprint)

2021 ◽  
Author(s):  
George Pappy ◽  
Melissa Aczon ◽  
Randall Wetzel ◽  
David Ledbetter
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
Airway Pressure ◽  
Input Data ◽  
Positive Airway Pressure ◽  
High Flow ◽  
Learning Models ◽  
High Flow Nasal Cannula ◽  
Non Invasive ◽  
Machine Learning Models

BACKGROUND High Flow Nasal Cannula (HFNC) provides non-invasive respiratory support for critically ill children who may tolerate it more readily than other Non-Invasive (NIV) techniques such as Bilevel Positive Airway Pressure (BiPAP) and Continuous Positive Airway Pressure (CPAP). Moreover, HFNC may preclude the need for mechanical ventilation (intubation). Nevertheless, NIV or intubation may ultimately be necessary for certain patients. Timely prediction of HFNC failure can provide an indication for increasing respiratory support. OBJECTIVE This work developed and compared machine learning models to predict HFNC failure. METHODS A retrospective study was conducted using the Virtual Pediatric Intensive Care Unit database of Electronic Medical Records (EMR) of patients admitted to a tertiary pediatric ICU from January 2010 to February 2020. Patients <19 years old, without apnea, and receiving HFNC treatment were included. A Long Short-Term Memory (LSTM) model using 517 variables (vital signs, laboratory data and other clinical parameters) was trained to generate a continuous prediction of HFNC failure, defined as escalation to NIV or intubation within 24 hours of HFNC initiation. For comparison, seven other models were trained: a Logistic Regression (LR) using the same 517 variables, another LR using only 14 variables, and five additional LSTM-based models using the same 517 variables as the first LSTM and incorporating additional ML techniques (transfer learning, input perseveration, and ensembling). Performance was assessed using the area under the receiver operating curve (AUROC) at various times following HFNC initiation. The sensitivity, specificity, positive and negative predictive values (PPV, NPV) of predictions at two hours after HFNC initiation were also evaluated. These metrics were also computed in a cohort with primarily respiratory diagnoses. RESULTS 834 HFNC trials [455 training, 173 validation, 206 test] met the inclusion criteria, of which 175 [103, 30, 42] (21.0%) escalated to NIV or intubation. The LSTM models trained with transfer learning generally performed better than the LR models, with the best LSTM model achieving an AUROC of 0.78, vs 0.66 for the 14-variable LR and 0.71 for the 517-variable LR, two hours after initiation. All models except for the 14-variable LR achieved higher AUROCs in the respiratory cohort than in the general ICU population. CONCLUSIONS Machine learning models trained using EMR data were able to identify children at risk for failing HFNC within 24 hours of initiation. LSTM models that incorporated transfer learning, input data perseveration and ensembling showed improved performance than the LR and standard LSTM models.

scholarly journals Leverage electron properties to predict phonon properties via transfer learning for semiconductors

2020 ◽  
Vol 6 (45) ◽  
pp. eabd1356
Author(s):  
Zeyu Liu ◽  
Meng Jiang ◽  
Tengfei Luo
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
Materials Informatics ◽  
Learning Models ◽  
Materials By Design ◽  
Property Relation ◽  
Composition Property ◽  
The Mean ◽  
Machine Learning Models ◽  
Phonon Properties

Electron properties are usually easier to obtain than phonon properties. The ability to leverage electron properties to help predict phonon properties can thus greatly benefit materials by design for applications like thermoelectrics and electronics. Here, we demonstrate the ability of using transfer learning (TL), where knowledge learned from training machine learning models on electronic bandgaps of 1245 semiconductors is transferred to improve the models, trained using only 124 data, for predicting various phonon properties (phonon bandgap, group velocity, and heat capacity). Compared to directly trained models, TL reduces the mean absolute errors of prediction by 65, 14, and 54% respectively, for the three phonon properties. The TL models are further validated using several semiconductors outside of the 1245 database. Results also indicate that TL can leverage not-so-accurate proxy properties, as long as they encode composition-property relation, to improve models for target properties, a notable feature to materials informatics in general.

Sign in / Sign up

Export Citation Format

Share Document