Goto

Collaborating Authors

Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset

arXiv.org Machine Learning

Clinical coding is currently a labour-intensive, error-prone, but critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new state of the art results. A popular dataset used in this task is MIMIC-III, a large intensive care database that includes clinical free text notes and associated codes. We argue for the reconsideration of the validity MIMIC-III's assigned codes that are often treated as gold-standard, especially when MIMIC-III has not undergone secondary validation. This work presents an open-source, reproducible experimental methodology for assessing the validity of codes derived from EHR discharge summaries. We exemplify the methodology with MIMIC-III discharge summaries and show the most frequently assigned codes in MIMIC-III are under-coded up to 35%.


On the Hardness of Problems Involving Negator Relationships in an Artificial Hormone System

arXiv.org Artificial Intelligence

The Artificial Hormone System (AHS) is a self-organizing middleware to allocate tasks in a distributed system. We extended it by so-called negator hormones to enable conditional task structures. However, this extension increases the computational complexity of seemingly simple decision problems in the system: In [1] and [2], we defined the problems Negator-Path and Negator-Sat and proved their NP-completeness. In this supplementary report to these papers, we show examples of Negator-Path and Negator-Sat, introduce the novel problem Negator-Stability and explain why all of these problems involving negators are hard to solve algorithmically.


Structure of Brain and Neurons. Examination of Rewiring in Brain.

#artificialintelligence

What do we say first when we talk about brain? We say that it is so complex that we still couldn't understand it completely. I will make an assumption for the structure of the brain and, I will examine the case which is mentioned in "The Brain That Remade Itself". Nerves are just binary switches. When they are used for an information, they are 1.


Classifying Natural Products from Plants, Fungi or Bacteria in the COCONUT Database

#artificialintelligence

Natural products (NPs) represent one of the most important resources for discovering new drugs. Here we asked whether NP origin can be assigned from their molecular structure in a subset of 60,171 NPs in the recently reported Collection of Open Natural Products (COCONUT) database assigned to plants, fungi, or bacteria. An online tool based on an SVM trained with the entire subset correctly assigned the origin of further NPs with similar performance (https://np-svm-map4.gdb.tools/). Origin information might be useful when searching for biosynthetic genes of NPs isolated from plants but produced by endophytic microorganisms.


Host Packet Buffer (HPB)

#artificialintelligence

In order to support multi-core CPUs and multithreaded host applications, ANIC SmartNICs utilize a flexible HPB technique. Host memory is segmented into a number of fixed size blocks. The block size is configurable but is typically 2MB or 4MB each. A collection of these host memory blocks is then dynamically pooled together to form a HPB. A specific application thread (often tied to a CPU core) is then explicitly assigned to a given HPB and will only process data that is "DMAed" into that HPB.