Milena Di Luca
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Milena Di Luca has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Annalisa Pace
Department of Sense Organs, Sapienza University of Rome, Rome, Italy
2 shared publications - Antonino Maniaci
Department of Medicine and Surgery, University of Enna “Kore”, Enna, Italy
2 shared publications - Christian Calvo-Henriquez
Service of Otolaryngology, Hospital Complex of Santiago de Compostela, Santiago de Compostela, Spain
2 shared publications - Claudio Vicini
University of Ferrara
2 shared publications - Giannicola Iannella
Department of Sense Organs, Sapienza University of Rome, 00185 Rome, Italy
2 shared publications - Giuseppe Magliulo
Department of ‘Organi di Senso’, University “Sapienza”, Viale dell’Università 33, 00185 Rome, Italy
2 shared publications
Latest Publications
- Open Access
Machine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study
Objectives: To evaluate the role of clinical scores assessing the risk of disease severity in patients with clinical suspicion of obstructive sleep apnea syndrome (OSA). The hypothesis was tested by applying artificial intelligence (AI) to demonstrate its effectiveness in distinguishing between mild–moderate OSA and severe OSA risk. Methods: A support vector machine model (SVM) was developed from the samples included in the analysis (N = 498), and they were split into 75% for training (N = 373) with the remaining for testing (N = 125). Two diagnostic thresholds were selected for OSA severity: mild to moderate (apnea–hypopnea index (AHI) ≥ 5 events/h and AHI < 30 events/h) and severe (AHI ≥ 30 events/h). The algorithms were trained and tested to predict OSA patient severity. Results: The sensitivity and specificity for the SVM model were 0.93 and 0.80 with an accuracy of 0.86; instead, the logistic regression full mode reported a value of 0.74 and 0.63, respectively, with an accuracy of 0.68. After backward stepwise elimination for features selection, the reduced logistic regression model demonstrated a sensitivity and specificity of 0.79 and 0.56, respectively, and an accuracy of 0.67. Conclusion: Artificial intelligence could be applied to patients with symptoms related to OSA to identify individuals with a severe OSA risk with clinical-based algorithms in the OSA framework.
Open AccessMachine Learning Identification of Obstructive Sleep Apnea Severity through the Patient Clinical Features: A Retrospective Study
Objectives: To evaluate the role of clinical scores assessing the risk of disease severity in patients with clinical suspicion of obstructive sleep apnea syndrome (OSA). The hypothesis was tested by applying artificial intelligence (AI) to demonstrate its effectiveness in distinguishing between mild–moderate OSA and severe OSA risk. Methods: A support vector machine model (SVM) was developed from the samples included in the analysis (N = 498), and they were split into 75% for training (N = 373) with the remaining for testing (N = 125). Two diagnostic thresholds were selected for OSA severity: mild to moderate (apnea–hypopnea index (AHI) ≥ 5 events/h and AHI < 30 events/h) and severe (AHI ≥ 30 events/h). The algorithms were trained and tested to predict OSA patient severity. Results: The sensitivity and specificity for the SVM model were 0.93 and 0.80 with an accuracy of 0.86; instead, the logistic regression full mode reported a value of 0.74 and 0.63, respectively, with an accuracy of 0.68. After backward stepwise elimination for features selection, the reduced logistic regression model demonstrated a sensitivity and specificity of 0.79 and 0.56, respectively, and an accuracy of 0.67. Conclusion: Artificial intelligence could be applied to patients with symptoms related to OSA to identify individuals with a severe OSA risk with clinical-based algorithms in the OSA framework.
- Open Access
- 31 August 2022
- Vol. 93 (4) , e2022263
Post-Cerebrovascular Stroke and Early Dysphagia Assessment: A Systematic Review.
We performed a systematic review on the early assessment of swallowing function after cerebrovascular stroke. A systematic review of the English language literature of the past 20 years was performed regarding swallowing function and cerebrovascular stroke. All articles reporting swallowing evaluation through clinical examination validated scores, and diagnostic tools were included in the summary. The systematic review of the literature identified 1,768 potentially relevant studies with 7 papers retrieved with a total of 589 stroke dysphagic patients. While at the clinical neurological assessment, The National Institutes of Health Stroke Scale was more frequently used as a clinical outcome predictor. The Bedside screening approach was carried out in 6 papers to assess patients with probable swallowing disorders. Among the diagnostic tools, seven studies performed the Flexible Fiberoptic Endoscopic evaluation assessing scoring validated system while two papers reported early swallowing outcomes Videofluoroscopic Swallow Study. Our systematic review revealed the findings significantly associated with dysphagia in post-cerebrovascular patients. Endoscopic evaluation of swallowing proved to be the most used method in the literature, effective in identifying early predictors of dysphagia. Given the presence of different assessing scores employed and reduced study samples enrolled, further studies with large courts are necessary for a greater significance.
- 31 August 2022
- Vol. 93 (4) , e2022263
Open AccessPost-Cerebrovascular Stroke and Early Dysphagia Assessment: A Systematic Review.
We performed a systematic review on the early assessment of swallowing function after cerebrovascular stroke. A systematic review of the English language literature of the past 20 years was performed regarding swallowing function and cerebrovascular stroke. All articles reporting swallowing evaluation through clinical examination validated scores, and diagnostic tools were included in the summary. The systematic review of the literature identified 1,768 potentially relevant studies with 7 papers retrieved with a total of 589 stroke dysphagic patients. While at the clinical neurological assessment, The National Institutes of Health Stroke Scale was more frequently used as a clinical outcome predictor. The Bedside screening approach was carried out in 6 papers to assess patients with probable swallowing disorders. Among the diagnostic tools, seven studies performed the Flexible Fiberoptic Endoscopic evaluation assessing scoring validated system while two papers reported early swallowing outcomes Videofluoroscopic Swallow Study. Our systematic review revealed the findings significantly associated with dysphagia in post-cerebrovascular patients. Endoscopic evaluation of swallowing proved to be the most used method in the literature, effective in identifying early predictors of dysphagia. Given the presence of different assessing scores employed and reduced study samples enrolled, further studies with large courts are necessary for a greater significance.