Diagnostic accuracy and reliability of smartphone captured radiologic images communicated via WhatsApp®

Ntja, Unathi; Rensburg, J. Janse van; Joubert, Gina

doi:10.1016/j.afjem.2021.11.001

Cited by 9 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…WhatsApp can offer a cost-effective, user-friendly, and efficient communication option in neurosurgical practice [ 4 , 5 ]. It proved to be useful for professional communication in different medical disciplines such as ophthalmology [ 6 ], emergency medicine [ 7 ], radiology [ 8 ], dermatology [ 9 ], orthopedics [ 10 ], pathology [ 11 ], and burn care [ 12 ]. WhatsApp facilitates physician-physician communication [ 13 ], improves medical care [ 14 ], and enhances decision-making [ 15 ].…”

Section: Discussionmentioning

confidence: 99%

WhatsApp-Based Record-Keeping System in a Private Neurosurgical Clinic Chain

Odeibat,

Hiasat,

Ibrahim

et al. 2023

Cureus

View full text Add to dashboard Cite

Background The demanding nature of neurosurgical practice requires a reliable system for documentation and record-keeping. The cost of electronic health record systems can limit their availability in low- and middle-income countries. That is why less expensive and easily accessible technological alternatives should be sought. In this article, we describe our adopted system for medical record-keeping based on WhatsApp (Meta Platforms, Inc., Menlo Park, CA). Methods In our chain of six clinics, each clinic has its record-keeping WhatsApp group dedicated to sharing medical data of outpatients following up in that specific clinic and of inpatients cared for in hospitals in its area. After each encounter, our surgeons share smartphone-captured pictures of their patients' medical data on the WhatsApp group of the related clinic. The medical data are then categorized and stored by the secretary on the clinic’s computer to be accessed at any time for record retrieval. Discussion Our five years of experience with the WhatsApp-based record-keeping system with medical records of 11,729 patients proved to be reliable, cost-effective, user-friendly, and efficient, and it positively impacted patient care. Responsible behavior, security precautions, and regulating policies are essential to protect patient confidentiality. Conclusion Our system can be an inexpensive alternative to the electronic health record system in small healthcare facilities. It can help physicians practicing in low- and middle-income countries to improve medical records documentation, thereby improving patient care. There is a need for policies to regulate the use of instant messaging applications in professional medical communication.

show abstract

Section: Discussionmentioning

confidence: 99%

WhatsApp-Based Record-Keeping System in a Private Neurosurgical Clinic Chain

Odeibat,

Hiasat,

Ibrahim

et al. 2023

Cureus

View full text Add to dashboard Cite

show abstract

“…The advent of smartphones coupled with high-speed internet has broken new frontiers in human connectivity and the way we disseminate and acquire information, especially in the fast-paced medical field. Digitized radiological images are conveniently transmitted from one location to another, even around the globe, within seconds on a regular basis for the purpose of consultation, timely diagnosis and patient management (Kotalwar et al., 2021; Ntja et al., 2022; Stahl et al., 2017; Westberg et al., 2017). In a highly imaging-dependent orthopaedic speciality, timely and accurate plain radiograph interpretation is paramount to supplement the history and physical examination findings in order to reach a diagnosis and deliver appropriate patient management (Giordano et al., 2015; Gulacti et al., 2016; Naqvi et al., 2014; Stahl et al., 2017, 2019).…”

Section: Introductionmentioning

confidence: 99%

Reliability of WhatsApp images of plain radiographs to diagnose fractures of the hand and wrist

Khoo

Guruseelan²,

Gunasagaran

et al. 2023

J Hand Surg Eur Vol

View full text Add to dashboard Cite

We assessed the reliability of plain radiographs interpreted through WhatsApp messaging system in orthopaedic hand trauma consultation in a large teaching hospital. Plain radiographs of 25 hand fractures and five normal radiographs were captured from a picture archiving and communication system using iPhone XS smartphone, anonymized and sent to 53 orthopaedic residents’ and consultants’ personal smartphones. The participants independently assessed the images and answered questions on fracture identification and characteristics, diagnostic confidence, further imaging and surgical inclination. The study was repeated after a 1-month washout period using the picture archiving and communication system on the hospital desktop. The results showed good (0.60 < ƙ < 0.80) intraobserver agreement on fracture identification and characteristics. The overall diagnostic accuracy for hand fractures was 95% on WhatsApp and 99% on the desktop. In conclusion, images of plain radiographs transmitted via WhatsApp were reliable for interpretation in orthopaedic hand trauma consultation. Level of evidence: IV

show abstract

“…In recent years, smartphone penetration has significantly increased, especially in LMICs, with over 90% ownership and around 50% mobile internet connectivity 3 . This presents new opportunities for the quick and easy sharing of radiographic images to aid clinical decision-making 4 . Studies have shown that smartphone-captured radiographic images, communicated through messaging applications like WhatsApp, demonstrate similar diagnostic accuracy compared to viewing images on full-featured PACS systems 4 .…”

Section: Introductionmentioning

confidence: 99%

“…This presents new opportunities for the quick and easy sharing of radiographic images to aid clinical decision-making 4 . Studies have shown that smartphone-captured radiographic images, communicated through messaging applications like WhatsApp, demonstrate similar diagnostic accuracy compared to viewing images on full-featured PACS systems 4 . In these approaches, a CXR image captured via smartphone or digital camera is transmitted to radiologists for remote review and diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Challenges of AI driven diagnosis of chest X-rays transmitted through smart phones: a case study in COVID-19

Antony,

Kakileti,

Shah

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Healthcare delivery during the initial days of outbreak of COVID-19 pandemic was badly impacted due to large number of severely infected patients posing an unprecedented global challenge. Although the importance of Chest X-rays (CXRs) in meeting this challenge has now been widely recognized, speedy diagnosis of CXRs remains an outstanding challenge because of fewer Radiologists. The exponential increase in Smart Phone ownership globally, including LMICs, provides an opportunity for exploring AI-driven diagnostic tools when provided with large volumes of CXRs transmitted through Smart Phones. However, the challenges associated with such systems have not been studied to the best of our knowledge. In this paper, we show that the predictions of AI-driven models on CXR images transmitted through Smart Phones via applications, such as , suffer both in terms of Predictability and Explainability, two key aspects of any automated Medical Diagnosis system. We find that several existing Deep learning based models exhibit prediction instability–disagreement between the prediction outcome of the original image and the transmitted image. Concomitantly we find that the explainability of the models deteriorate substantially, prediction on the transmitted CXR is often driven by features present outside the lung region, clearly a manifestation of Spurious Correlations. Our study reveals that there is significant compression of high-resolution CXR images, sometimes as high as 95%, and this could be the reason behind these two problems. Apart from demonstrating these problems, our main contribution is to show that Multi-Task learning (MTL) can serve as an effective bulwark against the aforementioned problems. We show that MTL models exhibit substantially more robustness, 40% over existing baselines. Explainability of such models, when measured by a saliency score dependent on out-of-lung features, also show a 35% improvement. The study is conducted on WaCXR dataset, a curated dataset of 6562 image pairs corresponding to original uncompressed and compressed CXR images. Keeping in mind that there are no previous datasets to study such problems, we open-source this data along with all implementations.

show abstract

Diagnostic accuracy and reliability of smartphone captured radiologic images communicated via WhatsApp®

Cited by 9 publications

References 12 publications

WhatsApp-Based Record-Keeping System in a Private Neurosurgical Clinic Chain

WhatsApp-Based Record-Keeping System in a Private Neurosurgical Clinic Chain

Reliability of WhatsApp images of plain radiographs to diagnose fractures of the hand and wrist

Challenges of AI driven diagnosis of chest X-rays transmitted through smart phones: a case study in COVID-19

Contact Info

Product

Resources

About