We read with interest the article by Kulkarni et al. , which highlights the advances in EKG pattern-recognition to help screen and identify patients with early-stage chronic diseases, particularly type 2 Diabetes (T2D).
While we recognize the rationale behind the inclusion criteria of the DISFIN study, the included population has a high insulin resistance-diabetes prevalence. However, it is important to note that the participants have a uniformly low A1c value and the time of exposure to hyperglycemia and treatment regimens are unknown.  These two variables are essential to consider since both have been described to have a direct relationship with micro and macrovascular complications that could impact EKG features and, thus, the performance of this model. 
Kulkarni et al.  do not clarify time since diagnosis of pre-diabetes or T2D and what treatment regimen each patient is undergoing. We ponder if patient classification based on the time of diagnosis, level of hyperglycemia and treatment regimen could help us better understand the onset and biological mechanisms behind EKG feature changes that help better identify subjects with hyperglycemia in all of its spectrum from pre-diabetes to T2D.
When choosing the ML technique, we noticed that the authors used a K-Fold Cross-Validation scenario for the six candidates. In our opinion, this may result in inconsistencies and skewness on the “K” folds of subsets of the dataset,...
When choosing the ML technique, we noticed that the authors used a K-Fold Cross-Validation scenario for the six candidates. In our opinion, this may result in inconsistencies and skewness on the “K” folds of subsets of the dataset, mainly because of the imbalance in the dataset. We would favor using a Stratified K-Fold Cross-Validation, an extension of the regular K-Fold Cross-Validation. This technique avoids such inconsistencies by maintaining the class-ratio of the data while generating the “K” subsets of the data. Thus, the same class distribution occurs when these “K” folds are concatenated to form the final complete dataset. Also, using Synthetic Minority Oversampling Technique (SMOTE) may result in an increased overlapping of classes and can bring in additional noise. For this, we suggest combining SMOTE with an undersampling technique, specifically Edited Nearest Neighbour (ENN), which removes the data points on the class boundary, increasing the separation between classes and reducing possible bias.
1.Kulkarni AR, Patel AA, Pipal KV, et alMachine-learning algorithm to non-invasively detect diabetes and pre-diabetes from electrocardiogramBMJ Innovations 2023;9:32-42.
2.Stratton, I. M., Adler, A. I., Neil, H. A., Matthews, D. R., Manley, S. E., Cull, C. A., Hadden, D., Turner, R. C., & Holman, R. R. (2000). Association of glycaemia with macrovascular and microvascular complications of type 2 diabetes (UKPDS 35): prospective observational study. BMJ (Clinical research ed.), 321(7258), 405–412. https://doi.org/10.1136/bmj.321.7258.405
For home manage in the territorial context in which I work, the Covid19 patient is advised to have a thermometer and oximeter , possibly also check blood pressure and blood sugar (if previously monitored ).
The simple urinalysis is not mentioned: it is cheap and can be performed at home.
In fact, through a strip that is immersed in urine, after 1-2 minutes we can obtain about 10 parameters.
They indicate not only kidney damage (presence of proteins, red blood cells, white blood cells, nitrites for urinary infections) but also important systemic metabolic indices.
The values of pH, urinary density, glycosuria and ketonuria indicate whether metabolic decompensations, dehydration, etc. are in progress; finally, also bilirubin and urobilinogen, for what concerns the liver or eventual haemolytic anemia.
I say this because unfortunately Covid19 can also compromise not only the kidney system, as well as a series of complications with a sneaky onset, not always quickly diagnosed.
There remains the problem of the stripes packaging, not available individually, from which a single dose will have to be obtained.
But it is probably a problem that can be overcome
We read with great interest the paper by Clement et al. With the advancement of technology, the digital consultations got a lot of attention in a good way and become more useful during the pandemic for both patients with disability as well as the normal patients. Though, some people still prefers to see the doctor face to face for more self-satisfaction. The digital consultation still have a long way to go for its acceptance within people specifically who are not used to and just begin.
As we know that telemedicine or video consultation can be used if you want to have look at a patient in care home, are working in a remote practice or the patient is bed bound. It saves patients an unnecessary trip to the practice, and the practitioner may have time freed up to see the sickest patients first.  Under the COVID-19 pandemic situation, people have to beware of the existence of such approaches to consultations, during the pandemic people were afraid to go to the hospital or clinic to have a treatment or appointment with doctor, especially for the aging population.
In Taiwan, the COVID-19 case raised up to hundreds local cases per day since Mid of May 2021 and the situation is going up to stage 3, the ministry of the health in Taiwan announced that people should prefer to use the digital consultation or telemedicine services to prevent the patients hospital visits and infection spread. Taiwan has a well-structured Health IT infrastructure an...
In Taiwan, the COVID-19 case raised up to hundreds local cases per day since Mid of May 2021 and the situation is going up to stage 3, the ministry of the health in Taiwan announced that people should prefer to use the digital consultation or telemedicine services to prevent the patients hospital visits and infection spread. Taiwan has a well-structured Health IT infrastructure and the digital consultation services were provided before for certain services but now it has a great advantage in the pandemic situation where it is not only helpful for the aged care patients or patients with diability but also for normal stable patients.
It helps unnecessary hospital visits as well as continued social distancing with proper delivery of healthcare services. However, there are some challenges in the remote systems where the patients are not familiar with the digital technology usage and in that circumstances the video consultations services could be a problem such as in elderly care .
 Kathy Oxtoby. (07 July, 2020) The rapid rise of digital consultations since Covid-19. News, https://www.gmjournal.co.uk/the-rapid-rise-of-digital-consultations-sinc...
 Chien-Hao Lin, Wen-Pin Tseng, Jhong-Lin Wu, Joyce Tay, Ming-Tai Cheng, Hooi-Nee Ong, Hao-Yang Lin Image, Yi-Ying Chen, Chih-Hsien Wu, Jiun-Wei Chen, Shey-Ying Chen, Chang-Chuan Chan, Chien-Hua Huang, Shyr-Chyr Chen. A Double Triage and Telemedicine Protocol to Optimize Infection Control in an Emergency Department in Taiwan During the COVID-19 Pandemic: Retrospective Feasibility Study. J Med Internet Res. 2020 June 23;22(6):e20586. doi:10.2196/20586
 Yi-Yin Lin, PhD and Chin-Shan Huang, PhD. Gerontology Institute, Georgia State University, Atlanta, Georgia. Adult and Continuing Education, National Chung Cheng University, Chia-Yi, Taiwan. Aging in Taiwan: Building a Society for Active Aging and Aging in Place. The Gerontologist. March 12, 2015; No. 2, 176–183 doi:10.1093
The high incidence of sensitive patient data exchanged between physicians via Whatsapp and iMessage evidenced in this study demonstrate potential violations of the new General Data Protection Regulation (GDPR) due to come into effect in May 2018. The GDPR outlines specific requirements for the processing and storage of data of which patient data is arguably the most sensitive. Breaches are expected to generate fines of up to 4% of annual turnover or 20 million euro – for authorities such as the NHS and HSE, this is potentially catastrophic.
Images of Xrays, blood results or wounds, taken via the mobile device in a doctor’s pocket, can be streamed via the famously insecure Apple iCloud in the USA, and suggested for potential upload to social Apps such as Facebook by default. Such material shared via Apps such as Whatsapp are downloaded by default to the image gallery on a smartphone and streamed between all networked devices, whether the recipients open the message or not. Such images can contain EXIF data, such as geographical co-ordinates, date, time, make and model of device etc. Such images are required to be encrypted and stored securely with the patient’s medical notes.
It cannot be overstated that ‘free’ communications solutions such as iMessage, WhatsApp, Signal, Secure Chat etc. are not free at all - if cash is not being paid for an App, the data of the clinician and patient is the commodity being paid for the functionality. Typically Apps have...
It cannot be overstated that ‘free’ communications solutions such as iMessage, WhatsApp, Signal, Secure Chat etc. are not free at all - if cash is not being paid for an App, the data of the clinician and patient is the commodity being paid for the functionality. Typically Apps have access a range of material on the users’ smartphone, including contact lists (to access and download), calendars (to read and amend entries) email, SMS, iMessage etc. (to read and send communications to those in the contact lists without notifying the owner), microphone (to access and record) and location (to track). If we are being ‘cost aware’ is access to a doctors diary, address book, email, digital messages, microphone and location/movements actually a cost worth paying?
The danger posed by lost phones is indeed alarming, and the importance of thoroughly cleaning devices before they are upgraded or discarded cannot be overstated either.
Security and data protection must be a central concern, not only for health service administrators, but for clinicians who understand that confidential patient data is no trivial issue. Patients disclose intimate personal information with the understanding that it will be stored and communicated securely and safely.
There is a range of technical solutions for the appropriately secure, efficient communication of patient data – Apps such as Hospify for example. It is essential that clinicians are provided with access to approved technical solutions, digital professionalism training and regular technical updates by the health service urgently, if they are to adhere to the new GDPR and an avoidable data protection disaster is averted.