PMID- 38444563
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240307
IS  - 2666-7894 (Electronic)
IS  - 2666-7894 (Linking)
VI  - 12
DP  - 2024 Mar
TI  - Predicting the Climate Impact of Healthcare Facilities Using Gradient Boosting 
      Machines.
LID - 100155 [pii]
LID - 10.1016/j.cesys.2023.100155 [doi]
AB  - Health care accounts for 9-10% of greenhouse gas (GHG) emissions in the United 
      States. Strategies for monitoring these emissions at the hospital level are 
      needed to decarbonize the sector. However, data collection to estimate emissions 
      is challenging, especially for smaller hospitals. We explored the potential of 
      gradient boosting machines (GBM) to impute missing data on resource consumption 
      in the 2020 survey of a consortium of 283 hospitals participating in Practice 
      Greenhealth. GBM imputed missing values for selected variables in order to 
      predict electricity use and beef consumption (R(2)=0.82) and anesthetic gas 
      desflurane use (R(2)=0.51), using administrative data readily available for most 
      hospitals. After imputing missing consumption data, estimated GHG emissions 
      associated with these three examples totaled over 3 million metric tons of CO(2) 
      equivalent emissions (MTCO(2)e). Specifically, electricity consumption had the 
      largest total carbon footprint (2.4 MTCO(2)e), followed by beef (0.6 million 
      MTCO(2)e) and desflurane consumption (0.03 million MTCO(2)e) across the 283 
      hospitals. The approach should be applicable to other sources of hospital GHGs in 
      order to estimate total emissions of individual hospitals and to refine survey 
      questions to help develop better intervention strategies.
FAU - Yin, Hao
AU  - Yin H
AD  - Department of Economics, University of Southern California, Los Angeles, 
      California, USA, 90089.
FAU - Sharma, Bhavna
AU  - Sharma B
AD  - School of Architecture, University of Southern California, Los Angeles, 
      California, USA, 90089.
FAU - Hu, Howard
AU  - Hu H
AD  - Department of Population and Public Health Sciences, Keck School of Medicine, 
      University of Southern California, Los Angeles, California, USA, 90033.
FAU - Liu, Fei
AU  - Liu F
AD  - Department of Population and Public Health Sciences, Keck School of Medicine, 
      University of Southern California, Los Angeles, California, USA, 90033.
FAU - Kaur, Mehak
AU  - Kaur M
AD  - Department of Population and Public Health Sciences, Keck School of Medicine, 
      University of Southern California, Los Angeles, California, USA, 90033.
FAU - Cohen, Gary
AU  - Cohen G
AD  - Health Care Without Harm, Boston, Massachusetts, USA, 20190.
FAU - McConnell, Rob
AU  - McConnell R
AD  - Department of Population and Public Health Sciences, Keck School of Medicine, 
      University of Southern California, Los Angeles, California, USA, 90033.
FAU - Eckel, Sandrah P
AU  - Eckel SP
AD  - Department of Population and Public Health Sciences, Keck School of Medicine, 
      University of Southern California, Los Angeles, California, USA, 90033.
LA  - eng
GR  - P30 ES007048/ES/NIEHS NIH HHS/United States
PT  - Journal Article
DEP - 20231126
PL  - United States
TA  - Clean Environ Syst
JT  - Cleaner environmental systems
JID - 9918769387906676
PMC - PMC10909736
MID - NIHMS1967373
OTO - NOTNLM
OT  - Climate change
OT  - Healthcare facility
OT  - Machine learning
OT  - Missing data imputation
OT  - Sustainability
EDAT- 2024/03/06 06:44
MHDA- 2024/03/06 06:45
PMCR- 2025/03/01
CRDT- 2024/03/06 03:49
PHST- 2025/03/01 00:00 [pmc-release]
PHST- 2024/03/06 06:45 [medline]
PHST- 2024/03/06 06:44 [pubmed]
PHST- 2024/03/06 03:49 [entrez]
AID - 100155 [pii]
AID - 10.1016/j.cesys.2023.100155 [doi]
PST - ppublish
SO  - Clean Environ Syst. 2024 Mar;12:100155. doi: 10.1016/j.cesys.2023.100155. Epub 
      2023 Nov 26.