Back

Scaling laws in healthcare delivery. A Network Analysis Approach to outpatient referral networks across the Veterans Health Administration.

Ben-Ari, A. Y.; Bigeleisen, P. E.; George, H. L.

2024-11-06 health informatics
10.1101/2024.11.06.24316731 medRxiv
Show abstract

BACKGROUNDWe studied clinical referral networks across the Veterans Health Administration. Network attributes, referral counts and timeliness of services rendered were estimated and used to predict outpatient care performance. A scaling law for outpatient referrals was derived, predicting an economy of scale. METHODSNetwork topology and operational statistics were estimated and their relationships were studied. A comparative study of multiple networks was undertaken. RESULTSWe observed similarities both in network structure and in the referral patterns. These are invariant of the healthcare system size. A power scaling law for referrals was inferred with an infra-linear exponent. CONCLUSIONStudy of referral networks across multiple healthcare systems shows an economy of scale and self-similarity between network attributes that are patient size invariant.

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.