Increased medicalisation of AFib patients using wearables
This is basically what we feared when Apple developed ECG capabilities for their watch. Overtreatment of the young, healthy, and wealthy.
“Our cohort study is among the first studies to systematically characterize the use of wearable use among individuals with AF as a part of routine health care delivery. Individuals who used wearables were younger, healthier, and socioeconomically better off than those who did not use wearables. We found no difference in clinic-measured pulse rates between the 2 groups but higher health care use rates among individuals who used wearables”
Deep Learning and Transfer Learning used to detect ARDS on Chest X-rays
In this article by Sjoding et al. in The Lancet Digital Health the authors
sought to train a deep convolutional neural network (CNN) to detect ARDS findings on chest radiographs.
They were able to produce concistent results:
a CNN could detect ARDS with an area under the receiver operator characteristics curve (AUROC) of 0·92 (95% CI 0·89–0·94).
[…] In an external cohort of 958 chest radiographs from 431 patients with sepsis, the AUROC was 0·88 (95% CI 0·85–0·91).
They were presented with a requiring problem in AI assisted digital health:
Generating large datasets for many medical problems can be challenging because clinical data might not be annotated for the finding of interest during routine care.
They were able to use Transfer Learning to accomodate this challenge:
Transfer learning is a machine-learning approach where knowledge gained from one problem can be used to help solve related problems.
[…] When training a CNN to detect ARDS, we hypothesised that if the network could first learn to extract general features from chest radiographs by pretraining the CNN to identify other common findings on chest radiographic studies, it might be able to borrow many of these features, reducing the number of annotated images necessary to train the network to detect findings of ARDS.
[…] We used transfer learning by first pretraining the network on 595 506 radiographs from two centres labelled for common descriptive chest findings (eg, opacity, effusion), but not ARDS. We then trained the network on 8073 radiographs annotated for ARDS. We tested the resulting network on an internal and external test set to evaluate its generalisation performance.
In summary, these results show the power of deep learning models, which can be trained to accurately identify chest radiographs consistent with ARDS. Further research is needed to evaluate how the use of these algorithms could support real-time identification of ARDS patients to ensure fidelity with evidence-based care or to support ongoing ARDS research.
The researchers also were also able to visualise the CNN activations on the chest X-rays. In a clinical setting this can help physicians quickly assess the accuracy of the algorithm.
Their study did have some limitations. The researchers state that ARDS is a syndrome and is not defined by a Gold standard, making uniform diagnosis impossible.
I also found basis for possible race bias. There’s a major race inconsistency between the training and external datasets (9% vs 30% blacks).
Using AI to prognosticate COVID-19 patients
In this study, Zhicheng Jiao et al., attempt to prognosticate COVID-19 patients based on a combination of AI, chest X-rays, and clinical data. Note that the research is partially funded by a for-profit organisation.
Although the wording in the article would suggest that the algorithm is accurate, the authors do cite this major limitation at the end:
This study has several limitations. First, the artificial intelligence model showed decreased performance on the external testing set relative to the internal testing set, indicating that generalisation might not be possible.
There’s also a basic design flaw, which is often seen in AI studies. The authors reduce the complicated medical conditions of the subjects into artificial binary oucomes: severe or not-severe outcome.
Disease outcome severity was defined as critical if the patient had any of the following outcomes: utilisation of mechanical ventilation, admission to the ICU, or death
One can argue that there’s some difference in severity between a patient receiving mechanical ventilation and one that dies.
Also, both sensitivy and specificity of the model, when tested on external data, are between 0.60 and 0.70, which is not very impressive. Use of the model would result in many both false positive and negative cases, and I’m not even sure it would fare any better than a clinician observing the patient.
Google enters digital dermatology
Time for other digital dermatology companies to pack up and leave the scene.
AI for Coronary Artery Disease
The EU has approved an AI technology that can identify people at risk of a fatal heart attack, years before it strikes. The CE marked tool uses AI and deep-learning technology to produce a fat attenuation index score (FAI-Score), which accurately measures inflammation of blood vessels in and around the heart.
But keep in mind that CE marking does not say anything about effectivity, efficience, sensitivy or specificity.
Abbott Ultreon 1.0 software merges optical coherence tomography (OCT), an imaging tool that provides cardiologists a view inside an artery or blood vessel, with AI technology for enhanced visualisation.
This combined technology can detect the severity of calcium-based blockages and measure vessel diameter to improve the precision of surgeon’s decision-making during coronary stenting procedures.
eMeistring
Pandemien resulterer i stadig nye elektroniske behandlingsmuligheter. Nå er der tilbud via HelseNorge til de med:
sosial fobi
panikklidelse, eller
moderat depresjon
eMeistring er veiledet psykologisk behandling via internett. Innholdet i behandlingen er evidensbasert og basert på kognitiv atferdsterapi. Kontakten mellom terapeut og pasient skjer skriftlig via nettet. Behandlingsprogrammet har vist seg å være like effektiv som ansikt-til-ansikt-behandling. To av tre pasienter som har gått gjennom behandlingsopplegget har fått god effekt.
Metoden stimulerer til en aktiv pasientrolle, og gjør det mulig for pasienten å gjennomføre behandlingen når som helst og hvor som helst. Det vil gjøre det enklere for personer som bor langt fra sitt distriktspsykiatriske senter (DPS), og for de som har vanskelig for å ta fri fra jobb på dagtid.
