Detection of arterial pressure waveform error using machine learning trained algorithms.

In critically ill and high-risk surgical room patients, an invasive arterial catheter is often inserted to continuously measure arterial pressure (AP). The arterial waveform pressure measurement, however, may be compromised by damping or inappropriate reference placement of the pressure transducer. Clinicians, decision support systems, or closed-loop applications that rely on such information would benefit from the ability to detect error from the waveform alone. In the present study we hypothesized that machine-learning trained algorithms could discriminate three types of transducer error from accurate monitoring with receiver operator characteristic (ROC) curve areas greater than 0.9. After obtaining written consent, patient arterial line waveform data was collected in the operating room in real-time during routine surgery requiring arterial pressure monitoring. Three deliberate error conditions were introduced during monitoring: Damping, Transducer High, and Transducer Low. The waveforms were split up into 10 s clips that were featurized. The data was also either calibrated against the patient's own baseline or left uncalibrated. The data was then split into training and validation sets, and machine-learning algorithms were run in a Monte-Carlo fashion on the training data with variable sized training sets and hyperparameters. The algorithms with the highest balanced accuracy were pruned, then the highest performing algorithm in the training set for each error state (High, Low, Damped) for both calibrated and uncalibrated data was finally tested against the validation set and the ROC and precision-recall curve area-under the curve (AUC) calculated. 38 patients were enrolled in the study with a mean age of 52 ± 15 years. A total of 40 h of monitoring time was recorded with approximately 120,000 heart beats featurized. For all error states, ROC AUCs for algorithm performance on classification of the state were greater than 0.9; when using patient-specific calibrated data AUCs were 0.94, 0.95, and 0.99 for the transducer low, transducer high, and damped conditions respectively. Machine-learning trained algorithms were able to discriminate arterial line transducer error states from the waveform alone with a high degree of accuracy.

Trends in the Surgical Management of Known or Suspected Differentiated Thyroid Cancer at a Single Institution, 2010-2018.

Background: The surgical management of nodular thyroid disease has been influenced by the advent of molecular diagnostics and recent guidelines recommending a more conservative approach to low-risk thyroid tumors. The purpose of this study was to assess practice changes arising from the early adoption of current literature within a single high-volume center. Methods: A retrospective cohort study of all patients evaluated or surgically treated for known or suspected thyroid cancer at a single institution was performed (2010-2018). We analyzed the yield of diagnostic thyroidectomy for indeterminate (Bethesda III and IV) nodules, the choice of initial operation for likely malignant (Bethesda V and VI) nodules, and the rate of completion thyroidectomy. The Cochran-Armitage test was used to assess the significance of any observed trends. Results: Of 2497 patients who underwent initial thyroidectomy from 2010 to 2018, 1791 patients had a tissue diagnosis of suspected or known thyroid cancer by cytopathology (Bethesda III-VI) or surgical pathology (differentiated thyroid cancer). In patients with likely malignant nodules but no clinical evidence of invasive or metastatic disease, the proportion managed with total thyroidectomy plus prophylactic neck dissection fell from 50% to 10% (p = 0.007). The proportion with likely malignant nodules managed definitively with thyroid lobectomy rose from 2% to 19% (p < 0.001). The rate of completion thyroidectomy for thyroid cancer found in the initial lobectomy specimen declined from 73% to 26% (p < 0.001). Among all patients with cytologically indeterminate nodules (n = 1036), we observed a decrease in the rate of diagnostic thyroidectomy from 67% to 35% over the study period (p = 0.015). Conclusions: The early adoption of new diagnostic technology and management guidelines has manifested in a less aggressive surgical approach to known or suspected thyroid cancer. Long-term follow-up will be required to assess oncologic and patient-centered outcomes arising from this modern strategy.