Teaming-up nurses with ophthalmologists to expand the reach of eye care in a middle-income country: Validation of health data acquisition by nursing staff in a telemedicine strategy

Telemedicine can be used to conduct ophthalmological assessment of patients, facilitating patient access to specialist care. Since the teleophthalmology models require data collection support from other health professionals, the purpose of our study was to assess agreement between the nursing technician and the ophthalmologist in acquisition of health parameters that can be used for remote analysis as part of a telemedicine strategy. A cross-sectional study was conducted with 140 patients referred to an ophthalmological telediagnosis center by primary healthcare doctors. The health parameters evaluated were visual acuity (VA), objective ophthalmic measures acquired by autorefraction, keratometry, and intraocular pressure (IOP). Bland-Altman plots were used to analyze agreement between the nursing technician and the ophthalmologist. The Bland-Altman analysis showed a mean bias equal to zero for the VA measurements [95%-LoA: -0.25–0.25], 0.01 [95%-LoA: -0.86–0.88] for spherical equivalent (M), -0.08 [95%-LoA: -1.1–0.95] for keratometry (K) and -0.23 [95%-LoA: -4.4–4.00] for IOP. The measures had a high linear correlation (R [95%CI]: 0.87 [0.82–0.91]; 0.97 [0.96–0.98]; 0.96 [0.95–0.97] and 0.88 [0.84–0.91] respectively). The results observed demonstrate that remote ophthalmological data collection by adequately trained health professionals is viable. This confirms the utility and safety of these solutions for scenarios in which access to ophthalmologists is limited.

Mobile microscopy and telemedicine platform assisted by deep learning for the quantification of Trichuris trichiura infection

Soil-transmitted helminths (STH) are the most prevalent pathogens among the group of neglected tropical diseases (NTDs). The Kato-Katz technique is the diagnosis method recommended by the World Health Organization (WHO) although it often presents a decreased sensitivity in low transmission settings and it is labour intensive. Visual reading of Kato-Katz preparations requires the samples to be analyzed in a short period of time since its preparation. Digitizing the samples could provide a solution which allows to store the samples in a digital database and perform remote analysis. Artificial intelligence (AI) methods based on digitized samples can support diagnosis by performing an objective and automatic quantification of disease infection. In this work, we propose an end-to-end pipeline for microscopy image digitization and automatic analysis of digitized images of STH. Our solution includes (a) a digitization system based on a mobile app that digitizes microscope samples using a 3D printed microscope adapter, (b) a telemedicine platform for remote analysis and labelling, and (c) novel deep learning algorithms for automatic assessment and quantification of parasitological infections by STH. The deep learning algorithm has been trained and tested on 51 slides of stool samples containing 949 Trichuris spp. eggs from 6 different subjects. The algorithm evaluation was performed using a cross-validation strategy, obtaining a mean precision of 98.44% and a mean recall of 80.94%. The results also proved the potential of generalization capability of the method at identifying different types of helminth eggs. Additionally, the AI-assisted quantification of STH based on digitized samples has been compared to the one performed using conventional microscopy, showing a good agreement between measurements. In conclusion, this work has presented a comprehensive pipeline using smartphone-assisted microscopy. It is integrated with a telemedicine platform for automatic image analysis and quantification of STH infection using AI models.

The Remote Analysis of Breath Sound in COVID-19 Patients: A Series of Clinical cases (Preprint)

BACKGROUND Respiratory sounds have been recognized as a possible indicator of behavior and health. Computer analysis of these sounds can indicate of characteristic sound changes caused by COVID-19 and can be used for diagnosis of this illness OBJECTIVE The communication aim is development of fast remote computer-assistance diagnosis methods for COVID-19, based on analysis of respiratory sounds METHODS Fast Fourier transform (FFT) was applied for computer analysis of respiratory sounds recorded near the mouth of 14 COVID-19 patients (age 18-80) and 17 healthy volunteers (age from 5 to 48). Sampling rate was from 44 to 96 kHz. Unlike usual computer-assistance methods of diagnostics of illness, based on respiratory sound analysis, we propose to test the high frequency part of the FFT spectrum (2000-6000 Hz). RESULTS Comparing FFT spectrums of the respiratory sounds of the patients and volunteers we developed computer-assistance methods of COVID 19 diagnostics and determined numerical healthy-ill criterions. These criterions are independent of gender and age of the tested person. CONCLUSIONS The proposed computer methods, based on analysis of the FFT spectrums of respiratory sounds of the patients and volunteers, allows one to automatically diagnose COVID-19 with sufficiently high diagnostic values. These methods can be applied to develop noninvasive self-testing kits for COVID-19.

Mobile microscopy and telemedicine platform assisted by deep learning for quantification of Trichuris trichiura infection

Soil-transmitted helminths (STH) are the most prevalent pathogens among the group of neglected tropical diseases (NTDs). Kato-Katz technique is the diagnosis method recommended by WHO and although is generally more sensitive than other microscopic methods in high transmission settings, it often presents a decreased sensitivity in low transmission settings and it is labour intensive. Digitizing the samples could provide a solution which allows to store the samples in a digital database and perform remote analysis. Artificial intelligence methods based on digitized samples can support diagnostics efforts by support diagnostics efforts by performing an automatic and objective quantification of disease infection.In this work, we propose an end-to-end pipeline for microscopy image digitization and automatic analysis of digitized images of soil-transmitted helminths. Our solution includes (1) a digitalization system based on a mobile app that digitizes the microscope samples using a low-cost 3D-printed microscope adapter, (2) a telemedicine platform for remote analysis and labelling and (3) novel deep learning algorithms for automatic assessment and quantification of parasitological infection of STH.This work has been evaluated by comparing the STH quantification using both a manual remote analysis based on the digitized images and the AI-assisted quantification against the reference method based on conventional microscopy. The deep learning algorithm has been trained and tested on 41 slides of stool samples containing 949 eggs from 6 different subjects using a cross-validation strategy obtaining a mean precision of 98,44% and mean recall of 80,94%. The results also proved the potential of generalization capability of the method at identifying different types of helminth eggs.In conclusion, this work has presented a comprehensive pipeline using smartphone-based microscopy integrated with a telemedicine platform for automatic image analysis and quantification of STH infection using artificial intelligence models.

THE REMOTE ANALYSIS OF BREATH SOUND IN COVID-19 PATIENTS: A SERIES OF CLINICAL CASES

Background: Respiratory sounds have been recognized as a possible indicator of behavior and health. Computer analysis of these sounds can indicate of characteristic sound changes caused by COVID-19 and can be used for diagnosis of this illness. Purpose: The communication aim is development of fast remote computer-assistance diagnosis of COVID-19, based on analysis of respiratory sounds. Materials and Methods: Fast Fourier transform (FFT) was applied for analyses of respiratory sounds recorded near the mouth of 9 COVID-19 patients and 4 healthy volunteers. Sampling rate was 48 kHz. Results: Comparing of FFT spectrums of the respiratory sounds of the patients and volunteers we proposed numerical healthy-ill criterions. Conclusions: The proposed computer method, based on analysis of the FFT spectrums of respiratory sounds of the patients and volunteers, allows one to automatically diagnose COVID-19 with sufficiently high diagnostic values. This method can be applied at development of noninvasive self-testing kits for COVID-19.