Teledermatology: a Few Bulletpoints by the American Academy of Dermatology (AAD)

The AAD released a teledermatology position statement a few years ago which was currently being revised and we’re going to see how we may adapt it given new situation with telemedicine.

The existing statement divides Telemedicine in Dermatology into a “live interactive” and “store-and-forward teledermatology”… while really highlighting the importance of high quality teledermatology.

Another point is that we need to make sure that patients always have the choice:
- Patients can be forced to use telemedicine or otherwise be excluded
  - The AAD doesn’t want an insurer to require them to see telemedicine first.
- This freedom of choice also applied to the providers:
  - Dermatologists shouldn’t be be required to see patients by telemedicine, if they would prefer to see patients in person.
- The bottom line is choice for both sides here.

It’s also important that we hold up high standards as far as quality for:
- proper history taking
- proper documentation
- high quality photos.

Jules Lipoff. Teledermatology in the US. 8th World Congress of Teledermatology, Skin Imaging and AI in Skin diseases – November 2020

Artificial Intelligence In Health

Paraffin sections are classically stained with Hematoxylin-Eosin (HE) before being integrated in a glass slide. One step further takes us to the digital slide. These studies below highlight how deep ...

Combining different sources of data are the fundamentals of personalized medicine. The developed tools are called personomics. Dermatopathology digital slides thus constitute a data source and it can solve specific ...

In the last 15 to 20 years computing and data power have enabled us to digitize, a complete digital slide. Digital pathology is not only the creation of a digital ...

While building that robust evidence base and showing proof of concept launching pilot studies, how can we move further along to this product in practice implementation of AI ? That ...

Dermatology has been among the first in generating evidence and a robust evidence base for Telehealth to: develop technology and innovation increase access and appropriateness to measure outcomes. However, there ...

Telehealth vs Telemedecine The pandemic has catalyzed the adoption of telehealth. “Telehealth” refers to a broader scope of remote health care services than telemedicine. Telemedicine refers specifically to remote clinical ...

Health Data

The training of a model is influenced by: The amount and quality of Data it receives. The Processing Power: it is more expensive than you think and effective methods are ...

Overfitting Overfitting occurs when the model is accurate with the data it is supplied to predict and the model is quite accurate, so the training set and validation set agree. ...

Explainability is of upmost importance in health in general for explaining the benefit of the patient…and not the least gaining his or her trust. Explainability concerns the algorithmic solution and ...

Even if efforts are made to standardize the image collection (same position), there are distortions which can arise. These can sometimes be corrected but it is important to be aware ...

Taking a standardized clinical picture can help to compare images and enhance machine learning to recognize the conditions, especially when associated with clinical data. It is also of use when ...

The adage goes: garbage in garbage out, and this is especially true for machine learning models, since this data sets on which the models are trained and validated, are essential ...