A quantitative approach for the analysis of clinician recognition of acute respiratory distress syndrome using electronic health record data

Abstract

ImportanceDespite its efficacy, low tidal volume ventilation (LTVV) remains severely underutilized for patients with acute respiratory distress syndrome (ARDS). Physician under-recognition of ARDS is a significant barrier to LTVV use. We propose a computational method that addresses some of the limitations of the current approaches to automated measurement of whether ARDS is recognized by physicians.ObjectiveTo quantify patient and physician factors affecting physicians’ tidal volume selection and to build a computational model of physician recognition of ARDS that accounts for these factors.Design, setting, and participantsIn this cross-sectional study, electronic health record data were collected for 361 ARDS patients and 388 non-ARDS hypoxemic (control) patients in nine adult intensive care units at four hospitals between June 24 and December 31, 2013.MethodsStandardized tidal volumes (mL/kg predicted body weight) were chosen as a proxy for physician decision-making behavior. Using data-science approaches, we quantified the effect of eight factors (six severity of illness, two physician behaviors) on selected standardized tidal volumes in ARDS and control patients. Significant factors were incorporated in computational behavioral models of physician recognition of ARDS.ResultsHypoxemia severity and ARDS documentation in physicians’ notes were associated with lower standardized tidal volumes in the ARDS cohort. Greater patient height was associated with lower standardized tidal volumes (which is already normalized for height) in both ARDS and control patients. The recognition model yielded a mean (99% confidence interval) physician recognition of ARDS of 22% (9%-42%) for mild, 34% (19%-49%) for moderate, and 67% (41%-100%) for severe ARDS.Conclusions and relevanceIn this study, patient characteristics and physician behaviors were demonstrated to be associated with differences in ventilator management in both ARDS and control patients. Our model of physician ARDS recognition measurement accounts for these clinical variables, providing an electronic approach that moves beyond relying on chart documentation or resource intensive approaches.

The first step is recognizing there is a problem: a methodology for adjusting for variability in disease severity when estimating clinician performance

“…This inference is based on our previously developed model of physician recognition of ARDS. Previously, we quantified the impact of patient characteristics on physician recognition of ARDS and subsequent LTVV delivery, by comparing physician behavior with ARDS patients to physician behavior with a novel hypoxemic ‘control’ cohort [ 27 ]. We found that the largest confounding characteristics in both ARDS and control cohorts was patient height (reported as the sex-neutral ‘predicted body weight’).…”

“…R(h i ): institutional level recognition rates of mild, moderate, or severe patients [ 27 ] (Fig. 2 B).…”

“…The recognition rates, R(h i ), in Eq. 1 are for the whole ARDS cohort by hypoxemia severity, which we estimated in prior work via mixture model as 22% for mild hypoxemia (P a O 2 /F I O 2 in range 200-300 mmHg), 34% for moderate hypoxemia (P a O 2 /F I O 2 in range 100-200 mmHg), and 67% for severe (P a O 2 /F I O 2 < 100 mmHg) [ 27 ]. Expected recognition is rounded down to the nearest whole patient to account for the binary nature of ARDS diagnosis.…”

“…Research has demonstrated that while physician ‘buy-in’ for LTVV is high, ARDS under-recognition remains a major barrier to LTVV use [ 7 , 17 – 26 ]. Furthermore, there is significant evidence that patient characteristics, such as ARDS severity, strongly influence physician recognition of ARDS [ 7 , 15 , 17 , 19 , 21 , 27 ]. ARDS is diagnosed using the Berlin Definition [ 5 ], which is a set of clinical criteria that a patient must meet.…”

A Quantitative and Radiomics approach to monitoring ARDS in COVID-19 patients based on chest CT: a retrospective cohort study

“…Therefore, it is possible to use the traditional quantitative chest CT metrics, such as volume and density to monitor the existence of ARDS. However, to our knowledge, no studies have used quantitative results to monitor the ARDS in COVID-19, while few quantitative results were used in some diagnosis models [14].…”