Back

Approximate Reciprocal Relationship Between Two Cause-Specific Hazard Ratios in COVID-19 Data With Mutually Exclusive Events

Cetin, S.; Ulgen, A.; Li, W.; Sivgin, H.

2021-04-27 epidemiology
10.1101/2021.04.22.21255955 medRxiv
Show abstract

COVID-19 survival data presents a special situation where not only the time-to-event period is short, but also the two events or outcome types, death and release from hospital, are mutually exclusive, leading to two cause-specific hazard ratios (csHRd and csHRr). The eventual mortality/release outcome can also be analyzed by logistic regression to obtain odds-ratio (OR). We have the following three empirical observations concerning csHRd, csHRr and OR: (1) The magnitude of OR is an upper limit of the csHRd: | log(OR) | [&ge;] | log(csHRd)|. This relationship between OR and HR might be understood from the definition of the two quantities; (2) csHRd and csHRr point in opposite directions: log(csHRd){middle dot} log(csHRr) < 0; This relation is a direct consequence of the nature of the two events; and (3) there is a tendency for a reciprocal relation between csHRd and csHRr: csHRd [~] 1/csHRr. Though an approximate reciprocal trend between the two hazard ratios is in indication that the same factor causing faster death also lead to slow recovery by a similar mechanism, and vice versa, a quantitative relation between csHRd and csHRr in this context is not obvious. These resutls may help future analyses of COVID-19 data, in particular if the deceased samples are lacking.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.