Steven D. Schwaitzberg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Steven D. Schwaitzberg has a total of 109 co-authors. Here are the top co-authors by number of shared publications:
- Lora Anne Cavuoto
Department of Industrial and Systems Engineering, University at Buffalo, Buffalo, USA
8 shared publications - Suvranu De
Mechanical Engineering, FAMU-FSU College of Engineering, Tallahassee, Florida, USA
5 shared publications - Xavier Intes
Rensselaer Polytechnic Institute, Center for Modeling, Simulation and Imaging in Medicine, Troy, New York, United States
5 shared publications - Anirban Dutta
University of Texas at El Paso, USA
4 shared publications - Jack Norfleet
U.S. Army Futures Command, Combat Capabilities Development Command Soldier Center STTC, Orlando, FL, USA
3 shared publications - Yaoyu Fu
West China Hospital, Chengdu, Sichuan, China
3 shared publications
Latest Publications
- Open Access
- 17 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 7 (3) , 1-24
An Interpretable Transformer-Based Foundation Model for Cross-Procedural Skill Assessment Using Raw fNIRS Signals
Objective skill assessment in high-stakes procedural environments requires models that not only decode underlying cognitive and motor processes but also generalize across tasks, individuals, and experimental contexts. While prior work has demonstrated the potential of functional near-infrared spectroscopy (fNIRS) for evaluating cognitive-motor performance, existing approaches are often task-specific, rely on extensive preprocessing, and lack robustness to new procedures or conditions. Here, we introduce an interpretable transformer-based foundation model trained on minimally processed fNIRS signals for cross-procedural skill assessment. Pretrained using self-supervised learning on data from laparoscopic surgical tasks and endotracheal intubation (ETI), the model achieves >88% classification accuracy on all tasks, with Matthews Correlation Coefficient exceeding 0.91 on ETI. It generalizes to a novel emergency airway procedure—cricothyrotomy—using as few as 24 labeled samples and a lightweight (<3k parameter) adapter module, attaining an AUC greater than 85%. Interpretability is achieved via a novel channel attention mechanism—developed specifically for fNIRS—that identifies functionally coherent prefrontal sub-networks validated through ablation studies. Temporal attention patterns align with task-critical phases and capture stress-induced changes in neural variability, offering insight into dynamic cognitive states.
- 17 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 7 (3) , 1-24
Open AccessAn Interpretable Transformer-Based Foundation Model for Cross-Procedural Skill Assessment Using Raw fNIRS Signals
Objective skill assessment in high-stakes procedural environments requires models that not only decode underlying cognitive and motor processes but also generalize across tasks, individuals, and experimental contexts. While prior work has demonstrated the potential of functional near-infrared spectroscopy (fNIRS) for evaluating cognitive-motor performance, existing approaches are often task-specific, rely on extensive preprocessing, and lack robustness to new procedures or conditions. Here, we introduce an interpretable transformer-based foundation model trained on minimally processed fNIRS signals for cross-procedural skill assessment. Pretrained using self-supervised learning on data from laparoscopic surgical tasks and endotracheal intubation (ETI), the model achieves >88% classification accuracy on all tasks, with Matthews Correlation Coefficient exceeding 0.91 on ETI. It generalizes to a novel emergency airway procedure—cricothyrotomy—using as few as 24 labeled samples and a lightweight (<3k parameter) adapter module, attaining an AUC greater than 85%. Interpretability is achieved via a novel channel attention mechanism—developed specifically for fNIRS—that identifies functionally coherent prefrontal sub-networks validated through ablation studies. Temporal attention patterns align with task-critical phases and capture stress-induced changes in neural variability, offering insight into dynamic cognitive states.
- 4 May 2026
- Published by Elsevier in Journal of Surgical Education
- Vol. 83 (7) , 103968
Describing What Surgeons See: Visual Orientation Strategies in Laparoscopic Cholecystectomy Across Imaging Conditions
- 4 May 2026
- Published by Elsevier in Journal of Surgical Education
- Vol. 83 (7) , 103968
Describing What Surgeons See: Visual Orientation Strategies in Laparoscopic Cholecystectomy Across Imaging Conditions
- 21 October 2024
- Published by Elsevier in Journal of Surgical Education
- Vol. 81 (12) , 103299
Accommodating Learners: An Adaptive Approach to Surgical Hand Preparation With Crutches
- 21 October 2024
- Published by Elsevier in Journal of Surgical Education
- Vol. 81 (12) , 103299
Accommodating Learners: An Adaptive Approach to Surgical Hand Preparation With Crutches
- 17 September 2024
- Published by Springer Nature
- p. 563-578
Creating Opportunities for Tomorrow’s Leaders in Surgery
- 17 September 2024
- Published by Springer Nature
- p. 563-578
Creating Opportunities for Tomorrow’s Leaders in Surgery
- 26 July 2024
- Published by Wolters Kluwer Health in Annals of Surgery
- Vol. 281 (2) , 221-222
AI, Amazon, and the Atom Bomb Navigating the Consequences of Technological Innovations in Surgery
An abstract is unavailable. This article is available as a PDF only.
- 26 July 2024
- Published by Wolters Kluwer Health in Annals of Surgery
- Vol. 281 (2) , 221-222
AI, Amazon, and the Atom Bomb Navigating the Consequences of Technological Innovations in Surgery
An abstract is unavailable. This article is available as a PDF only.
- Open Access
- 1 March 2024
- Published by Turkish Journal of Surgery in Turkish Journal of Surgery
- Vol. 40 (1) , 47-53
Liver resection versus ablation in geriatric populations - Does one method impart improved in-hospital mortality?
Objective: This study aimed to compare surgical resection versus ablation for managing liver malignancies in patients 65 and older. Material and Methods: Cases with liver tumors were extracted from the NSQIP database for patients aged ≥65 years. Following propensity score matching, multivariate Cox regression was used for 30-day morbidity and mortality for liver resection and ablation. Results: Following a propensity score matching, 1048 patients were 1:1 matched for comorbid conditions. Patients stayed in the hospital three days longer after resection (pConclusion: Despite being a generally sicker patient population with worse underlying liver function, ablative techniques were associated with a lower risk of adverse outcomes when compared to more aggressive resection of primary malignant tumors of the liver.
- 1 March 2024
- Published by Turkish Journal of Surgery in Turkish Journal of Surgery
- Vol. 40 (1) , 47-53
Open AccessLiver resection versus ablation in geriatric populations - Does one method impart improved in-hospital mortality?
Objective: This study aimed to compare surgical resection versus ablation for managing liver malignancies in patients 65 and older. Material and Methods: Cases with liver tumors were extracted from the NSQIP database for patients aged ≥65 years. Following propensity score matching, multivariate Cox regression was used for 30-day morbidity and mortality for liver resection and ablation. Results: Following a propensity score matching, 1048 patients were 1:1 matched for comorbid conditions. Patients stayed in the hospital three days longer after resection (pConclusion: Despite being a generally sicker patient population with worse underlying liver function, ablative techniques were associated with a lower risk of adverse outcomes when compared to more aggressive resection of primary malignant tumors of the liver.
- Open Access
- 11 December 2023
- Published by MDPI AG in Brain Sciences
- Vol. 13 (12) , 1706
Distinguishing Laparoscopic Surgery Experts from Novices Using EEG Topographic Features
The study aimed to differentiate experts from novices in laparoscopic surgery tasks using electroencephalogram (EEG) topographic features. A microstate-based common spatial pattern (CSP) analysis with linear discriminant analysis (LDA) was compared to a topography-preserving convolutional neural network (CNN) approach. Expert surgeons (N = 10) and novice medical residents (N = 13) performed laparoscopic suturing tasks, and EEG data from 8 experts and 13 novices were analysed. Microstate-based CSP with LDA revealed distinct spatial patterns in the frontal and parietal cortices for experts, while novices showed frontal cortex involvement. The 3D CNN model (ESNet) demonstrated a superior classification performance (accuracy > 98%, sensitivity 99.30%, specificity 99.70%, F1 score 98.51%, MCC 97.56%) compared to the microstate based CSP analysis with LDA (accuracy ~90%). Combining spatial and temporal information in the 3D CNN model enhanced classifier accuracy and highlighted the importance of the parietal–temporal–occipital association region in differentiating experts and novices.
- 11 December 2023
- Published by MDPI AG in Brain Sciences
- Vol. 13 (12) , 1706
Open AccessDistinguishing Laparoscopic Surgery Experts from Novices Using EEG Topographic Features
The study aimed to differentiate experts from novices in laparoscopic surgery tasks using electroencephalogram (EEG) topographic features. A microstate-based common spatial pattern (CSP) analysis with linear discriminant analysis (LDA) was compared to a topography-preserving convolutional neural network (CNN) approach. Expert surgeons (N = 10) and novice medical residents (N = 13) performed laparoscopic suturing tasks, and EEG data from 8 experts and 13 novices were analysed. Microstate-based CSP with LDA revealed distinct spatial patterns in the frontal and parietal cortices for experts, while novices showed frontal cortex involvement. The 3D CNN model (ESNet) demonstrated a superior classification performance (accuracy > 98%, sensitivity 99.30%, specificity 99.70%, F1 score 98.51%, MCC 97.56%) compared to the microstate based CSP analysis with LDA (accuracy ~90%). Combining spatial and temporal information in the 3D CNN model enhanced classifier accuracy and highlighted the importance of the parietal–temporal–occipital association region in differentiating experts and novices.