Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of Milan
Abstract Background The Epidemiological Unit of the Agency for Health Protection of Milan (ATS) calculates several indicators, at hospital and at patients’ residence area level (group level of analysis), with monitoring and programming scopes. Outcome indicators are usually influenced by differences...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Health Services Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12913-025-13203-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226523358265344 |
|---|---|
| author | Cristina Mazzali Anita Andreano Pietro Magnoni Andrea Salvatori Deborah Testa Alberto Milanese Adele Zanfino Antonio Giampiero Russo |
| author_facet | Cristina Mazzali Anita Andreano Pietro Magnoni Andrea Salvatori Deborah Testa Alberto Milanese Adele Zanfino Antonio Giampiero Russo |
| author_sort | Cristina Mazzali |
| collection | DOAJ |
| description | Abstract Background The Epidemiological Unit of the Agency for Health Protection of Milan (ATS) calculates several indicators, at hospital and at patients’ residence area level (group level of analysis), with monitoring and programming scopes. Outcome indicators are usually influenced by differences in subject case-mix; therefore, adjustment methods are applied to compare each group level with mean ATS values. Inverse probability weighting (IPW) is explored as an alternative to multivariable generalized linear model (GLM), to overcome some limitations of the latter method. Methods To implement IPW, a multinomial logistic model, with group level as dependent and subject characteristics as independent variables, was used to estimate patient weights, which were subsequently stabilized and truncated. Checks on IPW assumptions and covariates balance were implemented both in a quantitative and in a graphical way. Comparisons on adjustment performed with fixed effects and random intercept multivariable GLM were performed and exemplified using three outcome indicators. Results IPW assumptions were satisfied for all the indicators, and covariate balance presented minor issues for group levels with the lowest number of cases/events. Case-mix adjustment performed with multivariable fixed effects GLM showed a tendency to overestimate raw values and was characterized by broad confidence intervals in the three case-example indicators. Adjusted values produced using random intercept multivariable GLM suffered from a shrinkage towards the mean effect, particularly evident in the indicators with the lowest number of cases. IPW-adjusted estimates differed from raw values only when substantial differences in covariates distribution were present. Conclusions Provided that appropriate checks are implemented, IPW adjustment is applicable in the context of healthcare quality evaluation and can be easily conveyed to healthcare managers for effective dissemination. |
| format | Article |
| id | doaj-art-b9f49f9d4bf84cd88d6a0f8d08e809d1 |
| institution | Kabale University |
| issn | 1472-6963 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Health Services Research |
| spelling | doaj-art-b9f49f9d4bf84cd88d6a0f8d08e809d12025-08-24T11:15:42ZengBMCBMC Health Services Research1472-69632025-08-0125111210.1186/s12913-025-13203-9Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of MilanCristina Mazzali0Anita Andreano1Pietro Magnoni2Andrea Salvatori3Deborah Testa4Alberto Milanese5Adele Zanfino6Antonio Giampiero Russo7Epidemiology Unit, Agency for Health Protection (ATS) of MilanEpidemiology Unit, Agency for Health Protection (ATS) of MilanEpidemiology Unit, Agency for Health Protection (ATS) of MilanEpidemiology Unit, Agency for Health Protection (ATS) of MilanEpidemiology Unit, Agency for Health Protection (ATS) of MilanEpidemiology Unit, Agency for Health Protection (ATS) of MilanEpidemiology Unit, Agency for Health Protection (ATS) of MilanEpidemiology Unit, Agency for Health Protection (ATS) of MilanAbstract Background The Epidemiological Unit of the Agency for Health Protection of Milan (ATS) calculates several indicators, at hospital and at patients’ residence area level (group level of analysis), with monitoring and programming scopes. Outcome indicators are usually influenced by differences in subject case-mix; therefore, adjustment methods are applied to compare each group level with mean ATS values. Inverse probability weighting (IPW) is explored as an alternative to multivariable generalized linear model (GLM), to overcome some limitations of the latter method. Methods To implement IPW, a multinomial logistic model, with group level as dependent and subject characteristics as independent variables, was used to estimate patient weights, which were subsequently stabilized and truncated. Checks on IPW assumptions and covariates balance were implemented both in a quantitative and in a graphical way. Comparisons on adjustment performed with fixed effects and random intercept multivariable GLM were performed and exemplified using three outcome indicators. Results IPW assumptions were satisfied for all the indicators, and covariate balance presented minor issues for group levels with the lowest number of cases/events. Case-mix adjustment performed with multivariable fixed effects GLM showed a tendency to overestimate raw values and was characterized by broad confidence intervals in the three case-example indicators. Adjusted values produced using random intercept multivariable GLM suffered from a shrinkage towards the mean effect, particularly evident in the indicators with the lowest number of cases. IPW-adjusted estimates differed from raw values only when substantial differences in covariates distribution were present. Conclusions Provided that appropriate checks are implemented, IPW adjustment is applicable in the context of healthcare quality evaluation and can be easily conveyed to healthcare managers for effective dissemination.https://doi.org/10.1186/s12913-025-13203-9Quality indicators health careRisk adjustmentInverse probability weightingElectronic health records |
| spellingShingle | Cristina Mazzali Anita Andreano Pietro Magnoni Andrea Salvatori Deborah Testa Alberto Milanese Adele Zanfino Antonio Giampiero Russo Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of Milan BMC Health Services Research Quality indicators health care Risk adjustment Inverse probability weighting Electronic health records |
| title | Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of Milan |
| title_full | Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of Milan |
| title_fullStr | Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of Milan |
| title_full_unstemmed | Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of Milan |
| title_short | Case-mix adjustment through inverse probability weighting to compare health indicators across territories or providers – an application in the agency for health protection of Milan |
| title_sort | case mix adjustment through inverse probability weighting to compare health indicators across territories or providers an application in the agency for health protection of milan |
| topic | Quality indicators health care Risk adjustment Inverse probability weighting Electronic health records |
| url | https://doi.org/10.1186/s12913-025-13203-9 |
| work_keys_str_mv | AT cristinamazzali casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan AT anitaandreano casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan AT pietromagnoni casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan AT andreasalvatori casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan AT deborahtesta casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan AT albertomilanese casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan AT adelezanfino casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan AT antoniogiampierorusso casemixadjustmentthroughinverseprobabilityweightingtocomparehealthindicatorsacrossterritoriesorprovidersanapplicationintheagencyforhealthprotectionofmilan |