Prediction of Postoperative Deterioration in Cardiac Surgery Patients Using Electronic Health Record and Physiologic Waveform Data.

BACKGROUND: Postoperative hemodynamic deterioration among cardiac surgical patients can indicate or lead to adverse outcomes. Whereas prediction models for such events using electronic health records or physiologic waveform data are previously described, their combined value remains incompletely defined. The authors hypothesized that models incorporating electronic health record and processed waveform signal data (electrocardiogram lead II, pulse plethysmography, arterial catheter tracing) would yield improved performance versus either modality alone. METHODS: Intensive care unit data were reviewed after elective adult cardiac surgical procedures at an academic center between 2013 and 2020. Model features included electronic health record features and physiologic waveforms. Tensor decomposition was used for waveform feature reduction. Machine learning-based prediction models included a 2013 to 2017 training set and a 2017 to 2020 temporal holdout test set. The primary outcome was a postoperative deterioration event, defined as a composite of low cardiac index of less than 2.0 ml min-1 m-2, mean arterial pressure of less than 55 mmHg sustained for 120 min or longer, new or escalated inotrope/vasopressor infusion, epinephrine bolus of 1 mg or more, or intensive care unit mortality. Prediction models analyzed data 8 h before events. RESULTS: Among 1,555 cases, 185 (12%) experienced 276 deterioration events, most commonly including low cardiac index (7.0% of patients), new inotrope (1.9%), and sustained hypotension (1.4%). The best performing model on the 2013 to 2017 training set yielded a C-statistic of 0.803 (95% CI, 0.799 to 0.807), although performance was substantially lower in the 2017 to 2020 test set (0.709, 0.705 to 0.712). Test set performance of the combined model was greater than corresponding models limited to solely electronic health record features (0.641; 95% CI, 0.637 to 0.646) or waveform features (0.697; 95% CI, 0.693 to 0.701). CONCLUSIONS: Clinical deterioration prediction models combining electronic health record data and waveform data were superior to either modality alone, and performance of combined models was primarily driven by waveform data. Decreased performance of prediction models during temporal validation may be explained by data set shift, a core challenge of healthcare prediction modeling.

The role of gender and distance mentoring in the surgical education research fellowship.

OBJECTIVE: The nature of the mentor-mentee relationship is important in the pursuit of successful research projects. The purpose of this study is to evaluate the mentor-mentee relationships in the Surgical Education Research Fellowship (SERF) based on gender and geographical distances regarding program completion. We hypothesize that there are no differences for SERF program completion rates based on gender pairs and distances between pairs. METHODS: This was a retrospective study from 2006 to 2011. Mentor-mentee rosters were retrospectively reviewed for program completion, demographics, and PubMeD indexing. Time zone differences and geographic distances between pairs were found with online applications. Chi-square tests were used for categorical variables and nonparametric statistics were carried out using α = 0.05. RESULTS: Of the 82 individuals accepted into the SERF program, 43 (52%) completed the SERF program during the study period. There were no differences in program completion rates based on fellow gender and gender pairing (all p > 0.05). Different-gender pairs that completed the program (n = 17) were indexed more frequently on PubMed than same-gender pairs that completed the program (n = 24) (41% vs 12%, p = 0.04). There were no differences in program completion based on time zone differences (p = 0.20). The median distance between pairs completing the program (n = 35) was greater than that for pairs not completing the program (n = 36) (1741 km [IQR: 895-3117 km] vs 991 km [IQR: 676-2601 km]; p = 0.03). CONCLUSION: Completion of the SERF program was independent of mentor-mentee gender pairs and time zone differences. There was greater geographical distance separating mentor-mentee pairs that completed the SERF program compared with pairs that did not complete the program. Distance mentoring is a successful and crucial element of the SERF program.