Evolving Healthcare Quality in Top Tertiary General Hospitals in China during the China Healthcare Reform (2010-2012) from the Perspective of Inpatient Mortality

Abstract

Healthcare reforms (HR) initiated by many countries impacts on healthcare systems worldwide. Being one of fast developing countries, China launched HR in 2009. Better understanding of its impact is helpful for China and others in further pursuit of HR. Here we evaluate inpatient mortality, a proxy to healthcare quality, in 43 top tertiary hospitals in China during this critical period. This is a hospital-based observational study with 8 million discharge summary reports (DSR) from 43 Chinese hospitals from 2010-2012. Using DSRs, we extract the vita status as the outcome, in addition to age, gender, diagnostic codes, and surgical codes. Nearly all hospitals have expanded their hospitalization capacities during this period. As of year 2010, inpatient mortality (IM) across hospitals varies widely from 2‰ to 20‰. Comparing IM of year 2011 and 2012 with 2010, the overall IM has been substantially reduced (OR = 0.883 and 0.766, p-values<0.001), showing steady improvements in healthcare quality. Surgical IM correlates with the overall IM (correlation = 0.60, p-value <0.001), but is less uniform. Over these years, surgical IM has also been steadily reduced (OR = 0.890 and 0.793, p-values<0.001). Further analyses of treatments on five major diseases and six major surgeries revealed that treatments of myocardial infarction, cerebral hemorrhage and cerebral infarction have significant improvement. Observed temporal and spatial variations demonstrate that there is a substantial disparity in healthcare quality across tertiary hospitals, and that these hospitals are rapidly improving healthcare quality. Evidence-based assessment shed light on the reform impact. Lessons learnt here are relevant to further refining HR.

Fig 1. Computed ratios of discharge numbers in year 2011 (blue dots) and in year 2012 (green triangles) over discharge numbers in year 2010 (solid red line as the reference) across all 43 hospitals (organized by their geographic regions); nearly all ratios exceed one, corresponding to the increase of hospitalization capacity in these two years over the reference year.

Fig 2. “Point-Direction” plots show inpatient mortality (multiplied by 1000, i.e., per thousand) in year 2010 (red dots) and their directional changes in year 2011 (blue arrow) and in year 2012 (green arrow) across all 43 hospitals: a) the overall inpatient mortality, and b) inpatient mortality of all surgeries.

To represent statistical significances on temporal changes, computed p-values are transformed to logarithmic scale (-log₁₀(p-value)) and are shown either as a black dot (actual p-value) or black arrow (actual p-value is less than 10⁻⁴).

Fig 3. Correlation analysis of estimated inpatient mortalities of all surgeries (per thousand) with the overall inpatient mortalities (per thousand) over all 43 hospitals.

While their correlation coefficient at 0.60 (p-value <0.001) is statistically significant, there are hospitals with modest overall inpatient mortality but very high surgery-related inpatient mortality.