Clinical Applications of AI in Pain Medicine DOI
Marco Cascella

Published: Jan. 1, 2024

Language: Английский

Artificial Intelligence for Regional Anesthesiology and Acute Pain Medicine in the 21st Century DOI
Kristopher M. Schroeder, Monika Nanda, Edward R. Mariano

et al.

Anesthesiology Clinics, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0

Comparison of diagnostic image modalities for the detection of Achilles tendon tendinopathy using ankle magnetic resonance imaging DOI Creative Commons
Joohyun Lee, Jee‐Young Lee, Keum Nae Kang

et al.

Frontiers in Physiology, Journal Year: 2025, Volume and Issue: 16

Published: May 23, 2025

Background A thickened Achilles tendon (AT) is one of the important morphological changes observed in tendinopathy (ATTP). Previous research studies have demonstrated that both thickness (ATT) and cross-sectional area (CSA) (ATCSA) are correlated with ATTP subjects. However, comparative value ATT ATCSA relation to not clear, no calculated optimal clinical threshold values ATCSA. The goal this was assess determine which parameter more sensitive predicting ATTP. Methods AT lesions were studied 31 subjects 36 asymptomatic who underwent ankle magnetic resonance imaging (A-MRI) showed evidence Axial T1-weighted A-MRI images obtained at level. We measured junction soleus gastrocnemius aponeurosis using an image analysis program. defined as thickest point margin. total region showing most pronounced inflammatory lesions. In addition, a subgroup by sex performed evaluate gender-specific diagnostic performance Results average 3.83 ± 0.76 mm control group 5.42 0.97 group. 46.49 7.12 2 82.59 29.71 had significantly higher (p < 0.001) than ROC curve 57.20 . responsiveness 87.1%, its precision 88.9%. 4.64 mm. 80.6%, 80.6%. compared under (AUC) for two analyzed methods. ATCSA’s AUC 0.95 (95% CI: 088–1.00), ATT’s 0.91 0.84–0.97). Conclusion Although ATTP, measurement parameter.

Language: Английский

Citations

0

Harnessing artificial intelligence for predicting and managing postoperative pain: a narrative literature review DOI
Ruba Sajdeya, Samer Narouze

Current Opinion in Anaesthesiology, Journal Year: 2024, Volume and Issue: 37(5), P. 604 - 615

Published: June 25, 2024

Purpose of review This examines recent research on artificial intelligence focusing machine learning (ML) models for predicting postoperative pain outcomes. We also identify technical, ethical, and practical hurdles that demand continued investigation research. Recent findings Current ML leverage diverse datasets, algorithmic techniques, validation methods to predictive biomarkers, risk factors, phenotypic signatures associated with increased acute chronic persistent opioid use. demonstrate satisfactory performance predict outcomes their prognostic trajectories, modifiable factors at-risk patients who benefit from targeted management strategies, show promise in prevention applications. However, further evidence is needed evaluate the reliability, generalizability, effectiveness, safety ML-driven approaches before integration into perioperative practices. Summary Artificial (AI) has potential enhance by providing more accurate personalized interventions. By leveraging algorithms, clinicians can better tailor treatment strategies accordingly. successful implementation needs address challenges data quality, complexity, ethical considerations. Future should focus validating AI-driven interventions clinical practice fostering interdisciplinary collaboration advance care.

Language: Английский

Citations

2

Predictors and indicators DOI Creative Commons
Jong Yeon Park

Korean journal of anesthesiology, Journal Year: 2024, Volume and Issue: 77(2), P. 173 - 174

Published: March 13, 2024

In the current issue of Korean Journal Anesthesiology (KJA), prediction-related words such as impact, predict, assessing, indicator, association, and effect are included in titles clinical research papers.Ju et al. [1] reported that COVID-19 infections eight weeks preoperatively were associated with an increase 30-day postoperative mortality.In study conducted by Park [2], a machine learning model constructed using facial expressions was superior predictor severe pain (numeric rating scale [NRS] ≥ 7), outperforming models from physiological signals.Jang [3] frequency-domain analysis photoplethysmography arterial blood pressure may assess hemodynamic status requiring fluid or vasoactive inotropic therapy after congenital heart surgery.Kim [4] development ventricular-arterial decoupling is poor outcomes liver transplantation.Preoperative acute hyperglycemia found to be delirium [5].Finally, Lee [6] applying ultrafiltration improved clot firmness, more pronounced improvement when pre-ultrafiltration maximum firmness-extrinsically activated test tissue factor reduced cardiopulmonary bypass.If anesthesiologists could make accurate predictions, patients diagnosed treated earlier, thus improving outcomes.A defined something event fact enables one anticipate future occurrence.An indicator specific, measurable observable characteristic, trait, used show progress has happened.Research studies aimed at discovering appropriate predictors indicators improve continuously being conducted.In KJA, [5] investigate relationship between delirium.In study, least fasting glucose level > 140 mg/dl random 180 within 24 h before surgical incision.Chronic HbA 1c 6.5% three months surgery.Postoperative psychiatrist Confusion Assessment Method.Among group, ratio chronic kidney disease intraoperative transfusion considerably higher than no group.Park [2] investigated outperformed analgesia nociception index vital signs predict intensity.In 155 expressions, scores, signs, self-assessed intensity based on NRS recorded postoperatively who underwent gastrectomy.Anesthesiologists should consider importance preoperative evaluations, predictors, for outcomes.

Language: Английский

Citations

0

Objective Monitoring of Pain Using High Frequency Heart Rate Variability—A Narrative Review DOI Creative Commons
Bill Hum,

Yusef Shibly,

Alexa Christophides

et al.

Digital Medicine and Healthcare Technology, Journal Year: 2024, Volume and Issue: 3

Published: Oct. 24, 2024

Managing pain when a patient cannot communicate, during anesthesia or critical illness, is challenge many clinicians face. Numerous subjective methods of evaluating have been developed to address this, for instance, the visual analog and numerical rating scale. Intraoperatively, objective monitoring in anesthetized patients assessed through hemodynamic parameters; however, these parameters may not always accurately reflect perception. The high-frequency heart rate variability index (HFVI), also known as analgesia nociception (ANI), commercially available device by MDoloris that objectively assesses based on electrocardiogram, sympathetic tone, parasympathetic tone. monitor displays value from 0–100, where <50 indicates >50 anti-nociception. Given its potential pain, numerous studies utilized this clinical non-clinical settings. As such, we conducted literature review using various search terms PubMed selected HFVI our inclusion criteria review. In review, discuss mechanisms which monitors assess along with results provide comprehensive summary interested considering use novel monitoring.

Language: Английский

Citations

0

Clinical Applications of AI in Pain Medicine DOI
Marco Cascella

Published: Jan. 1, 2024

Language: Английский

Citations

0