Modelling EHR timeseries by restricting feature interaction Machine Learning

Time series data are prevalent in electronic health records, mostly in the form of physiological parameters such as vital signs and lab tests. The patterns of these values may be significant indicators of patients' clinical states and there might be patterns that are unknown to clinicians but are highly predictive of some outcomes. Many of these values are also missing which makes it difficult to apply existing methods like decision trees. We propose a recurrent neural network model that reduces overfitting to noisy observations by limiting interactions between features. We analyze its performance on mortality, ICD-9 and AKI prediction from observational values on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset. Our models result in an improvement of 1.1% [p<0.01] in AU-ROC for mortality prediction under the MetaVision subset and 1.0% and 2.2% [p<0.01] respectively for mortality and AKI under the full MIMIC-III dataset compared to existing state-of-the-art interpolation, embedding and decay-based recurrent models.

Identification of Predictive Sub-Phenotypes of Acute Kidney Injury using Structured and Unstructured Electronic Health Record Data with Memory Networks Machine Learning

Acute Kidney Injury (AKI) is a common clinical syndrome characterized by the rapid loss of kidney excretory function, which aggravates the clinical severity of other diseases in a large number of hospitalized patients. Accurate early prediction of AKI can enable in-time interventions and treatments. However, AKI is highly heterogeneous, thus identification of AKI sub-phenotypes can lead to an improved understanding of the disease pathophysiology and development of more targeted clinical interventions. This study used a memory network-based deep learning approach to discover predictive AKI sub-phenotypes using structured and unstructured electronic health record (EHR) data of patients before AKI diagnosis. We leveraged a real world critical care EHR corpus including 37,486 ICU stays. Our approach identified three distinct sub-phenotypes: sub-phenotype I is with an average age of 63.03$ \pm 17.25 $ years, and is characterized by mild loss of kidney excretory function (Serum Creatinne (SCr) $1.55\pm 0.34$ mg/dL, estimated Glomerular Filtration Rate Test (eGFR) $107.65\pm 54.98$ mL/min/1.73$m^2$). These patients are more likely to develop stage I AKI. Sub-phenotype II is with average age 66.81$ \pm 10.43 $ years, and was characterized by severe loss of kidney excretory function (SCr $1.96\pm 0.49$ mg/dL, eGFR $82.19\pm 55.92$ mL/min/1.73$m^2$). These patients are more likely to develop stage III AKI. Sub-phenotype III is with average age 65.07$ \pm 11.32 $ years, and was characterized moderate loss of kidney excretory function and thus more likely to develop stage II AKI (SCr $1.69\pm 0.32$ mg/dL, eGFR $93.97\pm 56.53$ mL/min/1.73$m^2$). Both SCr and eGFR are significantly different across the three sub-phenotypes with statistical testing plus postdoc analysis, and the conclusion still holds after age adjustment.

How companies are Using AI in the Field of Patient Data Mining


One of the ways AI is and will continue t be helpful in the field of healthcare is allowing medical professionals the ability to create treatment plans as well as discovering the best suited methods for helping their patients; instead of having to battle the tread-wheel of bureaucracy, nurses and physicians can focus on doing their actual jobs. Since we are in the age of big data, patient information is becoming valuable as tech giants, such as IBM and Google, are becoming more involved in acquiring this information; therefore, companies are using AI in the field known as patient data mining in a variety of ways. The AI research branch of the company recently launched a project known as Google Deepmind Health which focuses on mining medical records with the goal of providing faster and better health services; the project can go through hundreds of thousands of medical data within minutes. Also, Google's life sciences are working on a data-collecting initiative that aims to apply some of the same algorithms used to power Goggle's search button to analyze what it is that makes a person healthy. Included in this is experimenting with technologies that monitor diseases such as a digital contact lens that might detect levels of blood sugar.

The Use of NLP to Extract Unstructured Medical Data From Text - insideBIGDATA


When working in healthcare, a lot of the relevant information for making accurate predictions and recommendations is only available in free-text clinical notes. Much of this data is trapped in free-text documents in unstructured form. This data is needed in order to make healthcare decisions. Hence, it is important to be able to extract data in the best possible way such that the information obtained can be analyzed and used. State-of-the-art NLP algorithms can extract clinical data from text using deep learning techniques such as healthcare-specific word embeddings, named entity recognition models, and entity resolution models.

Unsupervised Learning for Computational Phenotyping Machine Learning

With large volumes of health care data comes the research area of computational phenotyping, making use of techniques such as machine learning to describe illnesses and other clinical concepts from the data itself. The "traditional" approach of using supervised learning relies on a domain expert, and has two main limitations: requiring skilled humans to supply correct labels limits its scalability and accuracy, and relying on existing clinical descriptions limits the sorts of patterns that can be found. For instance, it may fail to acknowledge that a disease treated as a single condition may really have several subtypes with different phenotypes, as seems to be the case with asthma and heart disease. Some recent papers cite successes instead using unsupervised learning. This shows great potential for finding patterns in Electronic Health Records that would otherwise be hidden and that can lead to greater understanding of conditions and treatments. This work implements a method derived strongly from Lasko et al., but implements it in Apache Spark and Python and generalizes it to laboratory time-series data in MIMIC-III. It is released as an open-source tool for exploration, analysis, and visualization, available at