Search Articles

View query in Help articles search

Search Results (1 to 10 of 102 Results)

Download search results: CSV END BibTex RIS

CSV download: Download all 102 search results (up to 5,000 articles maximum)

Revolutionizing Hypoglycemia Management in Long-Term Care: Lessons Learned From a Pilot Quality Improvement Initiative Using Continuous Glucose Monitoring

Revolutionizing Hypoglycemia Management in Long-Term Care: Lessons Learned From a Pilot Quality Improvement Initiative Using Continuous Glucose Monitoring

While successful incorporation of CGM into daily monitoring strategies can effectively reduce hypoglycemia as well as assist in the detection of hypoglycemic events [24], overcoming these practice barriers requires a comprehensive, stepwise implementation strategy to ensure staff are adequately trained and comfortable with the system. Quality improvement initiatives focusing on implementing CGM in LTC can serve as useful guides for overcoming practical challenges related to everyday practice [25,26].

Denis O'Donnell, Sue Burns, Shirley Drever, Lisa Quesnelle, Benjamin Yuen

JMIR Diabetes 2025;10:e73485


Daily Household Electricity Consumption in Community-Dwelling Older Individuals With Cognitive Impairment: Prospective Cohort Study

Daily Household Electricity Consumption in Community-Dwelling Older Individuals With Cognitive Impairment: Prospective Cohort Study

Therefore, early detection of MCI and subsequent early intervention are important [4]. However, most patients with cognitive decline visit a hospital after their symptoms have substantially progressed, and only a few patients visit a hospital while they are at the MCI stage [5]. Various researchers have attempted to develop assessment methods that allow for the screening of community-dwelling older individuals in their own homes.

Yuki Nakagawa, Shigeo Tanabe, Hikaru Kondo, Koki Tan, Soichiro Koyama, Shin Kitamura, Akiko Kada, Takuma Ishihara, Takuaki Yamamoto, Junya Denda, Hideaki Kimata, Taisuke Yamanaka, Ryosuke Umezawa, Yoshinobu Nakahashi, Yohei Otaka

JMIR Form Res 2025;9:e71265


Predicting Episodes of Hypovigilance in Intensive Care Units Using Routine Physiological Parameters and Artificial Intelligence: Derivation Study

Predicting Episodes of Hypovigilance in Intensive Care Units Using Routine Physiological Parameters and Artificial Intelligence: Derivation Study

Furthermore, its detection is labor-intensive, requiring frequent reevaluation and clinical interpretation using bedside instruments and questionnaires [10]. These instruments and questionnaires become even harder to use when patients and health care providers speak different languages [11].

Raphaëlle Giguère, Victor Niaussat, Monia Noël-Hunter, William Witteman, Tanya S Paul, Alexandre Marois, Philippe Després, Simon Duchesne, Patrick M Archambault

JMIR AI 2025;4:e60885


Automating Colon Polyp Classification in Digital Pathology by Evaluation of a “Machine Learning as a Service” AI Model: Algorithm Development and Validation Study

Automating Colon Polyp Classification in Digital Pathology by Evaluation of a “Machine Learning as a Service” AI Model: Algorithm Development and Validation Study

Recent developments in the fields of ML and AI, such as deep learning, for computer vision and object detection–related tasks [11-13] have led to a rapid uptake of the use of these tools in computational pathology research, where their utility has been widely recognized [14-17]. ML has traditionally required massive computational power and advanced knowledge of computer science and programming languages such as Python and R [18-20].

David Beyer, Evan Delancey, Logan McLeod

JMIR Form Res 2025;9:e67457


The Use of AI-Powered Thermography to Detect Early Plantar Thermal Abnormalities in Patients With Diabetes: Cross-Sectional Observational Study

The Use of AI-Powered Thermography to Detect Early Plantar Thermal Abnormalities in Patients With Diabetes: Cross-Sectional Observational Study

To improve the early detection of DFUs, it is important to develop and implement universal screening guidelines, increase awareness among patients and providers, and develop and implement better screening tools and methods. Medical thermography results from decades of research and development in the performance of infrared imaging equipment, standardization of technique, and clinical protocols for thermal imaging [11,12]. It could visualize diseases not readily detected or monitored by other methods.

Meshari F Alwashmi, Mustafa Alghali, AlAnoud AlMogbel, Abdullah Abdulaziz Alwabel, Abdulaziz S Alhomod, Ibrahim Almaghlouth, Mohamad-Hani Temsah, Amr Jamal

JMIR Diabetes 2025;10:e65209


Trade-Offs Between Simplifying Inertial Measurement Unit–Based Movement Recordings and the Attainability of Different Levels of Analyses: Systematic Assessment of Method Variations

Trade-Offs Between Simplifying Inertial Measurement Unit–Based Movement Recordings and the Attainability of Different Levels of Analyses: Systematic Assessment of Method Variations

An automatic carrying detection classifier [32] produces a binary mask of shape (Nframes, 1), which is applied as a filter to the posture and movement classifier outputs before computing the distributions. The distribution for each track is computed by taking the mean of the automatic carrying detection-filtered one-hot matrices along the frame axis to yield a vector of shape (1, Ncats).

Manu Airaksinen, Okko Räsänen, Sampsa Vanhatalo

JMIR Mhealth Uhealth 2025;13:e58078


Predictive Modeling of Acute Respiratory Distress Syndrome Using Machine Learning: Systematic Review and Meta-Analysis

Predictive Modeling of Acute Respiratory Distress Syndrome Using Machine Learning: Systematic Review and Meta-Analysis

Due to limited treatments, research has focused on early detection, with biomarkers and clinical scores like the Lung Injury Prediction Score and Early Acute Lung Injury Score [36]. However, the Lung Injury Prediction Score has a low positive predictive value, and Early Acute Lung Injury Score increases clinical workload without sufficient clinical evidence [37-39].

Jinxi Yang, Siyao Zeng, Shanpeng Cui, Junbo Zheng, Hongliang Wang

J Med Internet Res 2025;27:e66615


Comparison of Electronic Surveillance With Routine Monitoring for Patients With Lymphoma at High Risk of Relapse: Prospective Randomized Controlled Phase 3 Trial (Sentinel Lymphoma)

Comparison of Electronic Surveillance With Routine Monitoring for Patients With Lymphoma at High Risk of Relapse: Prospective Randomized Controlled Phase 3 Trial (Sentinel Lymphoma)

Early detection of relapse correlates with survival. In most cases, relapse is detected by the appearance of symptoms, clinical signs, or biological abnormalities [2-4]. Repeated surveillance computed tomography (CT) detects asymptomatic recurrence in only 1.7% of patients and increases the risk of secondary cancers because of radiation overexposure [5-8]. Circulating tumor DNA monitoring may be used to detect early recurrence before the onset of symptoms; however, this method has not been validated [9].

Katell Le Dû, Adrien Chauchet, Sophie Sadot-Lebouvier, Olivier Fitoussi, Bijou Fontanet, Arnaud Saint-Lezer, Frédéric Maloisel, Cédric Rossi, Sylvain Carras, Anne Parcelier, Magali Balavoine, Anne-Lise Septans

JMIR Cancer 2025;11:e65960


Vital Sign and Biochemical Data Collection Using Non-contact Photoplethysmography and the Comestai Mobile Health App: Protocol for an Observational Study

Vital Sign and Biochemical Data Collection Using Non-contact Photoplethysmography and the Comestai Mobile Health App: Protocol for an Observational Study

Early detection of changes in vital signs typically correlates with faster identification of changes in the patient’s health status and the escalation of care if necessary [8]. Alterations in vital signs preceding clinical deterioration are well documented, and the early identification of preventable outcomes is crucial for timely intervention [8]. Logically, the more frequently vital signs are measured, the quicker clinical deterioration can be detected.

Gianvincenzo Zuccotti, Paolo Osvaldo Agnelli, Lucia Labati, Erika Cordaro, Davide Braghieri, Simone Balconi, Marco Xodo, Fabrizio Losurdo, Cesare Celeste Federico Berra, Roberto Franco Enrico Pedretti, Paolo Fiorina, Sergio Maria De Pasquale, Valeria Calcaterra

JMIR Res Protoc 2025;14:e65229


Detecting Artificial Intelligence–Generated Versus Human-Written Medical Student Essays: Semirandomized Controlled Study

Detecting Artificial Intelligence–Generated Versus Human-Written Medical Student Essays: Semirandomized Controlled Study

In addition, studies often investigate the detection of texts written by chatbots using automatic tools or even detectors specifically designed for this purpose [18,25,27-30]. The detection rate of these detectors is often higher than that of human reviewers, but the accuracy can vary greatly depending on the text genre and the classifier used [14,31]. Moreover, linguistic features appear to be the most important subset of features influencing the performance of feature-based classifiers [2,5].

Berin Doru, Christoph Maier, Johanna Sophie Busse, Thomas Lücke, Judith Schönhoff, Elena Enax- Krumova, Steffen Hessler, Maria Berger, Marianne Tokic

JMIR Med Educ 2025;11:e62779