Daniel A. Donoho

Daniel A. Donoho

Auto-generated profile, based on publicly available information

Daniel A. Donoho

Division of Neurosurgery and Pediatrics, Children’s National Medical Center, Washington, DC, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2019 in Neurosurgery Clinics of North America
Verified
Journal Article
Closed access
DDDaniel A. Donoho
Daniel A. Donoho
ELEdward R. Laws
Edward R. Laws

1 January 2015 in Neurosurgery Clinics of North America
Verified
Journal Article
Closed access
DDDaniel Donoho
Daniel Donoho
GZGabriel Zada
Gabriel Zada

17 May 2022 in Scientific Reports
Verified
Journal Article
Open access
PDF file
DPDhiraj J. Pangal
Dhiraj J. Pangal
GKGuillaume Kugener
Guillaume Kugener
YZYichao Zhu
Yichao Zhu
ASAditya Sinha
Aditya Sinha
VUVyom Unadkat
Vyom Unadkat
DDDaniel A. Donoho
Daniel A. Donoho
Major vascular injury resulting in uncontrolled bleeding is a catastrophic and often fatal complication of minimally invasive surgery. At the outset of these events, surgeons do not know how much blood will be lost or whether they will successfully control the hemorrhage (achieve hemostasis). We evaluate the ability of a deep learning neural network (DNN) to predict hemostasis control ability using the first minute of surgical video and compare model performance with human experts viewing the same video. The publicly available SOCAL dataset contains 147 videos of attending and resident surgeons managing hemorrhage in a validated, high-fidelity cadaveric simulator. Videos are labeled with outcome and blood loss (mL). The first minute of 20 videos was shown to four, blinded, fellowship trained skull-base neurosurgery instructors, and to SOCALNet (a DNN trained on SOCAL videos). SOCALNet architecture included a convolutional network (ResNet) identifying spatial features and a recurrent network identifying temporal features (LSTM). Experts independently assessed surgeon skill, predicted outcome and blood loss (mL). Outcome and blood loss predictions were compared with SOCALNet. Expert inter-rater reliability was 0.95. Experts correctly predicted 14/20 trials (Sensitivity: 82%, Specificity: 55%, Positive Predictive Value (PPV): 69%, Negative Predictive Value (NPV): 71%). SOCALNet correctly predicted 17/20 trials (Sensitivity 100%, Specificity 66%, PPV 79%, NPV 100%) and correctly identified all successful attempts. Expert predictions of the highest and lowest skill surgeons and expert predictions reported with maximum confidence were more accurate. Experts systematically underestimated blood loss (mean error − 131 mL, RMSE 350 mL, R20.70) and fewer than half of expert predictions identified blood loss > 500 mL (47.5%, 19/40). SOCALNet had superior performance (mean error − 57 mL, RMSE 295 mL, R20.74) and detected most episodes of blood loss > 500 mL (80%, 8/10). In validation experiments, SOCALNet evaluation of a critical on-screen surgical maneuver and high/low-skill composite videos were concordant with expert evaluation. Using only the first minute of video, experts and SOCALNet can predict outcome and blood loss during surgical hemorrhage. Experts systematically underestimated blood loss, and SOCALNet had no false negatives. DNNs can provide accurate, meaningful assessments of surgical video. We call for the creation of datasets of surgical adverse events for quality improvement research.

18 March 2019 in International Forum of Allergy & Rhinology
Verified
Journal Article
Closed access
PDF file
DDDaniel A. Donoho
Daniel A. Donoho
CJCali E. Johnson
Cali E. Johnson
KHKevin T. Hur
Kevin T. Hur
IBIan A. Buchanan
Ian A. Buchanan
VFVance L. Fredrickson
Vance L. Fredrickson
BWBozena B. Wrobel
Bozena B. Wrobel

29 March 2019 in Operative Neurosurgery
Verified
Journal Article
Closed access
IBIan A Buchanan
Ian A Buchanan
EMElliot Min
Elliot Min
MPMartin H Pham
Martin H Pham
DDDaniel A Donoho
Daniel A Donoho
JBJoshua Bakhsheshian
Joshua Bakhsheshian
JLJohn C Liu
John C Liu
BACKGROUND AND IMPORTANCE: In an era of curtailed work hours and concerns over achieving technical proficiency in the repertoire of procedures necessary for independent practice, many residencies have turned to model simulation as an educational adjunct. Cerebrospinal fluid (CSF) leak repair after inadvertent durotomy in spine surgery is a fundamental skillset for any spine surgeon. While primary closure with suture is not always necessary for small durotomies, larger defects, on the other hand, must be repaired. However, the dire consequences of inadequate repair dictate that it is generally performed by the most experienced surgeon. Few intraoperative opportunities, therefore, exist for CSF leak repair by trainees. OBJECTIVE: To simulate dural repair in spine surgery using minimal-access techniques. METHODS: A cohort of 8 neurosurgery residents was evaluated on their durotomy repair efforts in a perfusion-based cadaveric model. RESULTS: Study participants demonstrated consistent improvement across trials, with a significant reduction in closure times between their initial (12 min, 7 sec ± 4 min, 43 sec) and final attempts (7 min, 4 sec ± 2 min, 6 sec; P = .02). Moreover, all trainees—irrespective of postgraduate year—were able to accomplish robust dural closures resistant to simulated Valsalva maneuvers. Participants reported high degrees of model realism and exhibited significant increases in postprocedure confidence scores. CONCLUSION: Our results support use of perfusion-based simulation models as a complement to neurosurgery training, as it affords unrestricted opportunities for honing psychomotor skillsets when resident learning is increasingly being challenged by work-hour limitations and stricter oversight in the context of value-based healthcare.

1 May 2019 in World Neurosurgery
Verified
Journal Article
Closed access
IBIan A. Buchanan
Ian A. Buchanan
MLMichelle Lin
Michelle Lin
DDDaniel A. Donoho
Daniel A. Donoho
LDLi Ding
Li Ding
SGSteven L. Giannotta
Steven L. Giannotta
JLJohn C. Liu
John C. Liu