Insufficiently precise diagnosis of clinical disease is likely responsible for many treatment failures, even for common conditions and treatments. With a large enough dataset, it may be possible to use unsupervised machine learning to define clinical disease patterns more precisely. We present an approach to learning these patterns by using probabilistic independence to disentangle the imprint on the medical record of causal latent sources of disease. We inferred a broad set of 2000 clinical signatures of latent sources from 9195 variables in 269,099 Electronic Health Records. The learned signatures produced better discrimination than the original variables in a lung cancer prediction task unknown to the inference algorithm, predicting 3-year malignancy in patients with no history of cancer before a solitary lung nodule was discovered. More importantly, the signatures' greater explanatory power identified pre-nodule signatures of apparently undiagnosed cancer in many of those patients.

The accuracy of predictive models for solitary pulmonary nodule (SPN) diagnosis can be greatly increased by incorporating repeat imaging and medical context, such as electronic health records (EHRs). However, clinically routine modalities such as imaging and diagnostic codes can be asynchronous and irregularly sampled over different time scales which are obstacles to longitudinal multimodal learning. In this work, we propose a transformer-based multimodal strategy to integrate repeat imaging with longitudinal clinical signatures from routinely collected EHRs for SPN classification. We perform unsupervised disentanglement of latent clinical signatures and leverage time-distance scaled self-attention to jointly learn from clinical signatures expressions and chest computed tomography (CT) scans. Our classifier is pretrained on 2,668 scans from a public dataset and 1,149 subjects with longitudinal chest CTs, billing codes, medications, and laboratory tests from EHRs of our home institution. Evaluation on 227 subjects with challenging SPNs revealed a significant AUC improvement over a longitudinal multimodal baseline (0.824 vs 0.752 AUC), as well as improvements over a single cross-section multimodal scenario (0.809 AUC) and a longitudinal imaging-only scenario (0.741 AUC). This work demonstrates significant advantages with a novel approach for co-learning longitudinal imaging and non-imaging phenotypes with transformers. Code available at https://github.com/MASILab/lmsignatures.

There are few decision yet which specifically address the question to what extent machine-learning aspects make a technical contribution. This decision explores whether using machine learning for improving the accuracy of medical billing codes makes a technical contribution. Here are the practical takeaways from the decision T 0755/18 (Semi-automatic answering/3M INNOVATIVE PROPERTIES) of 11.12.2020 of Technical Board of Appeal 3.5.07: Such billing codes may relate to a hospital stay of a patient based on a collection of the documents containing information about the medical procedures that were performed on the patient during the stay and other billable activities performed by hospital staff. This set of documents may be viewed as a corpus of evidence for the billing codes that need to be generated and provided to an insurer for reimbursement.

In this paper, we present an effective deep prediction framework based on robust recurrent neural networks (RNNs) to predict the likely therapeutic classes of medications a patient is taking, given a sequence of diagnostic billing codes in their record. Accurately capturing the list of medications currently taken by a given patient is extremely challenging due to undefined errors and omissions. We present a general robust framework that explicitly models the possible contamination through overtime decay mechanism on the input billing codes and noise injection into the recurrent hidden states, respectively. By doing this, billing codes are reformulated into its temporal patterns with decay rates on each medical variable, and the hidden states of RNNs are regularised by random noises which serve as dropout to improved RNNs robustness towards data variability in terms of missing values and multiple errors. The proposed method is extensively evaluated on real health care data to demonstrate its effectiveness in suggesting medication orders from contaminated values.

When we think about automation, typical examples -- factory floor robotics, spam filters, and automated software testing tools -- often come to mind. But what if automation could be given a dramatic upgrade, one made more intelligent by integrating these tools with machine learning (ML) technologies? Imagine a world in which automation tools watch how we work, then use artificial intelligence (AI)-driven insights to tell us how to work better (or upgrade our work efforts for us) on the fly. It's not a fantasy: Intelligent automation is arriving now, and it will profoundly change how we work. Today, automation tools are largely isolated and segmented into their own fiefdoms.