ai in healthcare
Since the start of the pandemic, new technologies have been developed to help reduce the spread of the infection.
Some of the most common safety measures today include measuring a person’s temperature, covering your nose and mouth with a mask, contact tracing, disinfection, and social distancing. Many businesses have adopted various technologies, including those with artificial intelligence (AI) underneath, helping to adhere to the COVID-19 safety measures.
As an example, numerous airlines, hotels, subways, shopping malls, and other institutions are already using thermal cameras to measure an individual’s temperature before people are allowed entry. In its turn, public transport in France relies on AI-based surveillance cameras to monitor whether or not people are social-distancing or wearing masks. Another example is requiring the download of contact-tracing apps delivered by governments across the globe.
However, there are a number of issues.
While many of these solutions help to ensure that COVID-19 prevention practices are observed, many of them have flaws or limits. In this article, we will cover some of the issues creating obstacles for fighting the pandemic.
Issue #1. Manual temperature scanning is tricky
Issue #2. Monitoring crowds is even more complex
Issue #3. Contact tracing leads to privacy concerns
Issue #4. UV rays harm eyes and skin
Issue #5. UVC robots are extremely expensive
Issue #6. No integration, no compliance, no transparency
Regardless of the safety measures in place and existing issues, innovations are already playing a vital role in the fight against COVID-19. By improving on existing technology, we can make everyone safer as we all adjust to the new normal.
read the details at https://www.altoros.com/blog/whats-wrong-with-ai-tools-and-devices-preventing-covid-19/
Lire l'article complet sur : www.altoros.com
“ATMAN AI”, an Artificial Intelligence algorithm that can detect the presence of COVID-19 disease in Chest X Rays, has been developed to combat COVID fatalities involving lung. ATMAN AI is used for chest X-ray screening as a triaging tool in Covid-19 diagnosis, a method for rapid identification and assessment of lung involvement. This is a joint effort of the DRDO Centre for Artificial Intelligence and Robotics (CAIR), 5C Network & HCG Academics. This will be utilized by online diagnostic startup 5C Network with support of HCG Academics across India.
Triaging COVID suspect patients using X Ray is fast, cost effective and efficient. It can be a very useful tool especially in smaller towns in India owing to lack of easy access to CT scans there.
This will also reduce the existing burden on radiologists and make CT machines which are being used for COVID be used for other diseases and illness owing to overload for CT scans.
The novel feature namely “Believable AI” along with existing ResNet models have improved the accuracy of the software and being a machine learning tool, the accuracy will improve continually.
Chest X-Rays of RT-PCR positive hospitalized patients in various stages of disease involvement were retrospectively analysed using Deep Learning & Convolutional Neural Network models by an indigenously developed deep learning application by CAIR-DRDO for COVID -19 screening using digital chest X-Rays. The algorithm showed an accuracy of 96.73%.
read more at http://indiaai.gov.in/news/drdo-cair-5g-network-and-hcg-academics-develop-atman-ai
Lire l'article complet sur : indiaai.gov.in
Numerous studies demonstrate frequent mutations in the genome of SARS-CoV-2. Our goal was to statistically link mutations to severe disease outcome.
We found that automated machine learning, such as the method of Tsamardinos and coworkers used here, is a versatile and effective tool to find salient features in large and noisy databases, such as the fast growing collection of SARS-CoV-2 genomes.
In this work we used machine learning techniques to select mutation signatures associated with severe SARS-CoV-2 infections. We grouped patients into 2 major categories (“mild” and “severe”) by grouping the 179 outcome designations in the GISAID database.
A protocol combined of logistic regression and feature selection algorithms revealed that mutation signatures of about twenty mutations can be used to separate the two groups. The mutation signature is in good agreement with the variants well known from previous genome sequencing studies, including Spike protein variants V1176F and S477N that co-occur with DG14G mutations and account for a large proportion of fast spreading SARS-CoV-2 variants. UTR mutations were also selected as part of the best mutation signatures. The mutations identified here are also part of previous, statistically derived mutation profiles.
An online prediction platform was set up that can assign a probabilistic measure of infection severity to SARS-CoV-2 sequences, including a qualitative index of the strength of the diagnosis. The data confirm that machine learning methods can be conveniently used to select genomic mutations associated with disease severity, but one has to be cautious that such statistical associations – like common sequence signatures, or marker fingerprints in general – are by no means causal relations, unless confirmed by experiments.
Our plans are to update the predictions server in regular time intervals. While this project was underway more than 100 thousand sequences were deposited in public databases, and importantly, new variants emerged in the UK and in South Africa that are not yet included in the current datasets. Also, in addition to mutations, we plan to include also insertions and deletions which will hopefully further improve the predictive power of the server.
The study was funded by the Hungarian Ministry for Innovation and Technology (MIT) , within the framework of the Bionic thematic programme of the Semmelweis University.
Read the entire study at https://www.biorxiv.org/content/10.1101/2021.04.01.438063v1.full
Access the online portal mentioned above at https://covidoutcome.com/
Lire l'article complet sur : www.biorxiv.org
Patient travel history can be crucial in evaluating evolving infectious disease events. Such information can be challenging to acquire in electronic health records, as it is often available only in unstructured text.
Objective: This study aims to assess the feasibility of annotating and automatically extracting travel history mentions from unstructured clinical documents in the Department of Veterans Affairs across disparate health care facilities and among millions of patients. Information about travel exposure augments existing surveillance applications for increased preparedness in responding quickly to public health threats.
Methods: Clinical documents related to arboviral disease were annotated following selection using a semiautomated bootstrapping process. Using annotated instances as training data, models were developed to extract from unstructured clinical text any mention of affirmed travel locations outside of the continental United States. Automated text processing models were evaluated, involving machine learning and neural language models for extraction accuracy.
Results: Among 4584 annotated instances, 2659 (58%) contained an affirmed mention of travel history, while 347 (7.6%) were negated. Interannotator agreement resulted in a document-level Cohen kappa of 0.776. Automated text processing accuracy (F1 85.6, 95% CI 82.5-87.9) and computational burden were acceptable such that the system can provide a rapid screen for public health events.
Conclusions: Automated extraction of patient travel history from clinical documents is feasible for enhanced passive surveillance public health systems.
Without such a system, it would usually be necessary to manually review charts to identify recent travel or lack of travel, use an electronic health record that enforces travel history documentation, or ignore this potential source of information altogether.
The development of this tool was initially motivated by emergent arboviral diseases. More recently, this system was used in the early phases of response to COVID-19 in the United States, although its utility was limited to a relatively brief window due to the rapid domestic spread of the virus.
Such systems may aid future efforts to prevent and contain the spread of infectious diseases.
read the study at https://publichealth.jmir.org/2021/3/e26719
Lire l'article complet sur : publichealth.jmir.org