mHealth-community health worker telemedicine intervention for surgical site infection diagnosis: a prospective study among women delivering via caesarean section in rural Rwanda

Smartphone applications for remote patient monitoring reduces clinic utilization after full-endoscopic spine surgery

INTRODUCTION

The rising number of outpatient spine surgeries creates challenges in postoperative management and care. Telemedicine offers a unique opportunity to reduce in-person clinic visits and improve resource allocation. We aimed to investigate the impact of a validated smartphone application on clinic utilization following full-endoscopic spine surgery (FESS).

METHODS

We evaluated patients undergoing FESS from 2020 to 2022 and a pre-COVID control group (CG) from 2018 to 2019. Subsequently, we divided the patients into three groups: one using the application (intervention group, IG), and two CGs (2020-2022, CG and 2018-2019, historical control group (HG)). We analyzed the post-surgical hospitalization rate, all follow-ups, and virtually transmitted patient-reported outcomes.

RESULTS

A total of 115 patients were included in the IG. The CG consisted of 137 and the HG of 202 patients (CG and HG in the following). Group homogeneity was satisfactory regarding patient age (p = 0.9), sex (p = 0.88), and body mass index (p = 0.99). IG patients were treated as outpatients significantly more often [14.78% vs. 29.2% vs. 37.62% (p < 0.001)]. Additionally, IG patients showed significantly higher follow-up compliance [74.78% vs. 40.14% vs. 37.13% (p < 0.001)] 3-month post-surgery and fewer in-patient follow-up visits [(0.5 ± 0.85 vs. 1.32 ± 0.8 vs. 1.33 ± 0.7 (p < 0.001)].

CONCLUSION

Our results underline the feasibility, efficacy, and safety of remote patient monitoring following FESS. Furthermore, they highlight the opportunity to implement a virtual wound checkup, and to substantially improve postoperative follow-up compliance via telemedicine.

Machine Learning Approaches for the Image-Based Identification of Surgical Wound Infections: Scoping Review

BACKGROUND

Surgical site infections (SSIs) occur frequently and impact patients and health care systems. Remote surveillance of surgical wounds is currently limited by the need for manual assessment by clinicians. Machine learning (ML)-based methods have recently been used to address various aspects of the postoperative wound healing process and may be used to improve the scalability and cost-effectiveness of remote surgical wound assessment.

OBJECTIVE

The objective of this review was to provide an overview of the ML methods that have been used to identify surgical wound infections from images.

METHODS

We conducted a scoping review of ML approaches for visual detection of SSIs following the JBI (Joanna Briggs Institute) methodology. Reports of participants in any postoperative context focusing on identification of surgical wound infections were included. Studies that did not address SSI identification, surgical wounds, or did not use image or video data were excluded. We searched MEDLINE, Embase, CINAHL, CENTRAL, Web of Science Core Collection, IEEE Xplore, Compendex, and arXiv for relevant studies in November 2022. The records retrieved were double screened for eligibility. A data extraction tool was used to chart the relevant data, which was described narratively and presented using tables. Employment of TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) guidelines was evaluated and PROBAST (Prediction Model Risk of Bias Assessment Tool) was used to assess risk of bias (RoB).

RESULTS

In total, 10 of the 715 unique records screened met the eligibility criteria. In these studies, the clinical contexts and surgical procedures were diverse. All papers developed diagnostic models, though none performed external validation. Both traditional ML and deep learning methods were used to identify SSIs from mostly color images, and the volume of images used ranged from under 50 to thousands. Further, 10 TRIPOD items were reported in at least 4 studies, though 15 items were reported in fewer than 4 studies. PROBAST assessment led to 9 studies being identified as having an overall high RoB, with 1 study having overall unclear RoB.

CONCLUSIONS

Research on the image-based identification of surgical wound infections using ML remains novel, and there is a need for standardized reporting. Limitations related to variability in image capture, model building, and data sources should be addressed in the future.

Late and Persistent Symptoms Suggestive of Surgical Site Infections After Cesarean Section: Results from a Prospective Cohort Study in Rural Rwanda

Background: Women in low-resource settings will likely develop late surgical site infections (SSIs), diagnosed after post-operative day (POD) 10. We measured SSI prevalence and predictors of late and persistent SSIs-suggestive symptoms among women who delivered via cesarean section (c-section). Patients and Methods: Women who underwent c-sections at Kirehe District Hospital (KDH) between September 2019 and February 2020 were prospectively enrolled. Data were collected on POD1, POD11, and POD30. Logistic regression identified factors associated with persistent and late SSI symptoms. Results: In total, 808 women were study enrolled. Of these, 646 women physically attended the POD11 clinic visit follow-up, while 671 received the POD30 telephone-based follow-up review. Thirty-three (5.0%) women were diagnosed with an SSI on POD11, and 39 (5.3%) had an SSI diagnosis during POD11 to POD30, giving a cumulative prevalence of 10.3% late SSI rate. Of 671, 400 (59.9%) reported at least one SSI-associated symptom between POD11 and POD30. The reported symptoms included pain (56.6%), fever (19.4%), or incision drainage (16.6%). Of these, 200 women reported still having at least one of these symptoms on POD30. Of the 400 women with late SSI symptoms, 232 (58.0%) did not seek care, and of these, 80 (48.5%), 59 (35.8%), and 15 (8.9%) could not afford transport fare, did not believe symptoms were severe for a medical visit, and were not able to travel, respectively. Lower odds of late SSI-suggestive symptoms were reported among women with health insurance (adjusted odds ratio [aOR], 0.06; p = 0.013), whereas higher late SSI-suggestive symptoms odds were among women with wealthier socioeconomic status (aOR, 2.88; p = 0.004). Conclusions: Women in rural Rwanda are at risk of late and persistent SSI-suggestive symptoms. Financial barriers and the perception that their symptoms were not serious enough for the medical visit need education on early care seeking and interventions to mitigate financial barriers for optimizing perinatal care.