Development, Validation, and Comparison of a Novel Nociception/Anti-Nociception Monitor against Two Commercial Monitors in General Anesthesia

In this paper, we present the development and the validation of a novel index of nociception/anti-nociception (N/AN) based on skin impedance measurement in time and frequency domain with our prototype AnspecPro device. The primary objective of the study was to compare the Anspec-PRO device with two other commercial devices (Medasense, Medstorm). This comparison was designed to be conducted under the same conditions for the three devices. This was carried out during total intravenous anesthesia (TIVA) by investigating its outcomes related to noxious stimulus. In a carefully designed clinical protocol during general anesthesia from induction until emergence, we extract data for estimating individualized causal dynamic models between drug infusion and their monitored effect variables. Specifically, these are Propofol hypnotic drug to Bispectral index of hypnosis level and Remifentanil opioid drug to each of the three aforementioned devices. When compared, statistical analysis of the regions before and during the standardized stimulus shows consistent difference between regions for all devices and for all indices. These results suggest that the proposed methodology for data extraction and processing for AnspecPro delivers the same information as the two commercial devices.

Combining Model-Agnostic Meta-Learning and Transfer Learning for Regression

For cases in which a machine learning model needs to be adapted to a new task, various approaches have been developed, including model-agnostic meta-learning (MAML) and transfer learning. In this paper, we investigate how the differences in the data distributions between the old tasks and the new target task impact performance in regression problems. By performing experiments, we discover that these differences greatly affect the relative performance of different adaptation methods. Based on this observation, we develop ensemble schemes combining multiple adaptation methods that can handle a wide range of data distribution differences between the old and new tasks, thus offering more stable performance for a wide range of tasks. For evaluation, we consider three regression problems of sinusoidal fitting, virtual reality motion prediction, and temperature forecasting. The evaluation results demonstrate that the proposed ensemble schemes achieve the best performance among the considered methods in most cases.

FedMSA: A Model Selection and Adaptation System for Federated Learning

Federated Learning (FL) enables multiple clients to train a shared model collaboratively without sharing any personal data. However, selecting a model and adapting it quickly to meet user expectations in a large-scale FL application with heterogeneous devices is challenging. In this paper, we propose a model selection and adaptation system for Federated Learning (FedMSA), which includes a hardware-aware model selection algorithm that trades-off model training efficiency and model performance base on FL developers' expectation. Meanwhile, considering the expected model should be achieved by dynamic model adaptation, FedMSA supports full automation in building and deployment of the FL task to different hardware at scale. Experiments on benchmark and real-world datasets demonstrate the effectiveness of the model selection algorithm of FedMSA in real devices (e.g., Raspberry Pi and Jetson nano).

Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France

The coronavirus disease 2019 (COVID-19) pandemic has urged many governments in the world to enforce a strict lockdown where all nonessential businesses are closed and citizens are ordered to stay at home. One of the consequences of this policy is a significant change in electricity consumption patterns. Since load forecasting models rely on calendar or meteorological information and are trained on historical data, they fail to capture the significant break caused by the lockdown and have exhibited poor performances since the beginning of the pandemic. In this paper we introduce two methods to adapt generalized additive models, alleviating the aforementioned issue. Using Kalman filters and fine-tuning allows to adapt quickly to new electricity consumption patterns without requiring exogenous information. The proposed methods are applied to forecast the electricity demand during the French lockdown period, where they demonstrate their ability to significantly reduce prediction errors compared to traditional models. Finally, expert aggregation is used to leverage the specificities of each predictions and enhance results even further.

The Effect of a Diverse Dataset for Transfer Learning in Thermal Person Detection

Thermal cameras are popular in detection for their precision in surveillance in the dark and for privacy preservation. In the era of data driven problem solving approaches, manually finding and annotating a large amount of data is inefficient in terms of cost and effort. With the introduction of transfer learning, rather than having large datasets, a dataset covering all characteristics and aspects of the target place is more important. In this work, we studied a large thermal dataset recorded for 20 weeks and identified nine phenomena in it. Moreover, we investigated the impact of each phenomenon for model adaptation in transfer learning. Each phenomenon was investigated separately and in combination. the performance was analyzed by computing the F1 score, precision, recall, true negative rate, and false negative rate. Furthermore, to underline our investigation, the trained model with our dataset was further tested on publicly available datasets, and encouraging results were obtained. Finally, our dataset was also made publicly available.

DTD: An R Package for Digital Tissue Deconvolution

Digital tissue deconvolution (DTD) estimates the cellular composition of a tissue from its bulk gene-expression profile. For this, DTD approximates the bulk as a mixture of cell-specific expression profiles. Different tissues have different cellular compositions, with cells in different activation states, and embedded in different environments. Consequently, DTD can profit from tailoring the deconvolution model to a specific tissue context. Loss-function learning adapts DTD to a specific tissue context, such as the deconvolution of blood, or a specific type of tumor tissue. We provide software for loss-function learning, for its validation and visualization, and for applying the DTD models to new data.

Efficient Reuse of Natural Language Processing Models for Phenotype-Mention Identification in Free-text Electronic Medical Records: A Phenotype Embedding Approach

Background

Much effort has been put into the use of automated approaches, such as natural language processing (NLP), to mine or extract data from free-text medical records in order to construct comprehensive patient profiles for delivering better health care. Reusing NLP models in new settings, however, remains cumbersome, as it requires validation and retraining on new data iteratively to achieve convergent results.

Objective

The aim of this work is to minimize the effort involved in reusing NLP models on free-text medical records.

Methods

We formally define and analyze the model adaptation problem in phenotype-mention identification tasks. We identify “duplicate waste” and “imbalance waste,” which collectively impede efficient model reuse. We propose a phenotype embedding–based approach to minimize these sources of waste without the need for labelled data from new settings.

Results

We conduct experiments on data from a large mental health registry to reuse NLP models in four phenotype-mention identification tasks. The proposed approach can choose the best model for a new task, identifying up to 76% waste (duplicate waste), that is, phenotype mentions without the need for validation and model retraining and with very good performance (93%-97% accuracy). It can also provide guidance for validating and retraining the selected model for novel language patterns in new tasks, saving around 80% waste (imbalance waste), that is, the effort required in “blind” model-adaptation approaches.

Conclusions

Adapting pretrained NLP models for new tasks can be more efficient and effective if the language pattern landscapes of old settings and new settings can be made explicit and comparable. Our experiments show that the phenotype-mention embedding approach is an effective way to model language patterns for phenotype-mention identification tasks and that its use can guide efficient NLP model reuse.

Cost-Effectiveness of Docetaxel and Paclitaxel for Adjuvant Treatment of Early Breast Cancer: Adaptation of a Model-Based Economic Evaluation From the United Kingdom to South Africa

OBJECTIVES

Transferability of economic evaluations to low- and middle-income countries through adaptation of models is important; however, several methodological and practical challenges remain. Given its significant costs and the quality-of-life burden to patients, adjuvant treatment of early breast cancer was identified as a priority intervention by the South African National Department of Health. This study assessed the cost-effectiveness of docetaxel and paclitaxel-containing chemotherapy regimens (taxanes) compared with standard (non-taxane) treatments.

METHODS

A cost-utility analysis was undertaken based on a UK 6-health-state Markov model adapted for South Africa using the Mullins checklist. The analysis assumed a 35-year time horizon. The model was populated with clinical effectiveness data (hazard ratios, recurrence rates, and adverse events) using direct comparisons from clinical trials. Resource use patterns and unit costs for estimating cost parameters (drugs, diagnostics, consumables, personnel) were obtained from South Africa. Uncertainty was assessed using probabilistic and deterministic sensitivity analyses.

RESULTS

The incremental cost per patient for the docetaxel regimen compared with standard treatment was R6774. The incremental quality-adjusted life years (QALYs) were 0.24, generating an incremental cost-effectiveness ratio of R28430 per QALY. The cost of the paclitaxel regimen compared with standard treatment was estimated as -R578 and -R1512, producing an additional 0.03 and 0.025 QALYs, based on 2 trials. Paclitaxel, therefore, appears to be a dominant intervention. The base case results were robust to all sensitivity analyses.

CONCLUSIONS

Based on the adapted model, docetaxel and paclitaxel are predicted to be cost-effective as adjuvant treatment for early breast cancer in South Africa.

Brazilian Analytical Decision Model for Cardiovascular Disease: An Adaptation of the Scottish Cardiovascular Disease Policy Model

INTRODUCTION

Despite the significant impact of cardiovascular disease (CVD), there is not yet an analytical decision tool for assessing efficiency of interventions to prevent primary CVD events in Brazil. Therefore, we sought to adapt a Scottish CVD Policy Model to be used in the proposed population.

METHODS

Calibration consisted of identifying multiplicative factors for linear predictors of existing survival analysis models to produce predictions that closely match observed data (Life-table and Brazilian cohort study). Target data were life expectancy (LE) and cumulative incidence of coronary heart disease (CHD), cerebrovascular disease (CBVD), fatal CVD and fatal non-CVD. Root-Mean-Square-Error (RMSE) was used to estimate differences between predictions and observations. Acceptance criteria were defined as a fit of less than one year for LE and 1% for cumulative incidence. Male and female models were built separately.

RESULTS

The original model underestimated LE (RMSE=2.85 for men and 1.91 for women), CHD and CBVD for women (RMSE=0.044 and 0.041, respectively). The calibration process identified multiplicative factors to reach acceptance criteria for the four target data mentioned above (RMSE=0.61, 0.21, 0.016 and 0.017, respectively). Over prediction was identified only for CHD events in men (RMSE=0.031) being further calibrated (RMSE=0.008). All other target data met the acceptance criteria. Overall, the calibrated model predicts properly to individuals aging 35-80 years old, diabetics or not, smokers or not, with or without family history of CVD, and presenting at least one of the risk factors uncontrolled: Systolic Blood Pressure, Total Cholesterol or HDL-Cholesterol.

DISCUSSION

This is the first decision analytic model capable of assessing efficiency of interventions that prevent primary CVD events in Brazil. In future research, independent external validation should be carried out to corroborate the reliability of the model outputs.