Predicting Disease Progress with Imprecise Lab Test Results

TL;DR

This paper introduces an imprecision range loss (IR loss) for deep learning models, specifically LSTM, to better handle laboratory test data with inherent measurement imprecision, improving disease progression predictions.

Contribution

It proposes a novel IR loss function that accounts for imprecise lab test results and integrates it into LSTM models for more stable disease prediction.

Findings

IR loss improves prediction stability on imprecise data

The method effectively incorporates imprecision ranges into training

Experimental results show enhanced prediction consistency

Abstract

In existing deep learning methods, almost all loss functions assume that sample data values used to be predicted are the only correct ones. This assumption does not hold for laboratory test data. Test results are often within tolerable or imprecision ranges, with all values in the ranges acceptable. By considering imprecision samples, we propose an imprecision range loss (IR loss) method and incorporate it into Long Short Term Memory (LSTM) model for disease progress prediction. In this method, each sample in imprecision range space has a certain probability to be the real value, participating in the loss calculation. The loss is defined as the integral of the error of each point in the impression range space. A sampling method for imprecision space is formulated. The continuous imprecision space is discretized, and a sequence of imprecise data sets are obtained, which is convenient for gradient descent learning. A heuristic learning algorithm is developed to learn the model parameters based on the imprecise data sets. Experimental results on real data show that the prediction method based on IR loss can provide more stable and consistent prediction result when test samples are generated from imprecision range.