医疗保险和医疗补助服务中心提供了来自公共数据的两个数据集，https://data.cms.gov。
-
cms_patient_experience包含一些来自“临终关怀 - 提供者数据”的经过轻微清理的数据，该数据提供了临终关怀机构的列表以及有关患者护理质量的一些数据，https://data.cms.gov/provider-data/dataset/252m-zfp9 。 -
cms_patient_care“2020 年医生和临床医生质量支付计划虚拟小组公开报告”，https://data.cms.gov/provider-data/dataset/8c70-d353
格式
cms_patient_experience 是一个包含 500 个观察值和五个变量的 DataFrame ：
- org_pac_id,org_nm
-
组织 ID 和名称
- measure_cd,measure_title
-
测量代码和标题
- prf_rate
-
衡量绩效率
cms_patient_care 是一个包含 252 个观测值和 5 个变量的 DataFrame ：
- ccn,facility_name
-
设施 ID 和名称
- measure_abbr
-
缩写的测量标题，适合用作变量名称
- score
-
测量分数
- type
-
分数是指满分 100 分 ("observed")，还是原始分数的最大可能值 ("denominator")
例子
cms_patient_experience %>%
dplyr::distinct(measure_cd, measure_title)
#> # A tibble: 6 × 2
#> measure_cd measure_title
#> <chr> <chr>
#> 1 CAHPS_GRP_1 CAHPS for MIPS SSM: Getting Timely Care, Appointments, and…
#> 2 CAHPS_GRP_2 CAHPS for MIPS SSM: How Well Providers Communicate
#> 3 CAHPS_GRP_3 CAHPS for MIPS SSM: Patient's Rating of Provider
#> 4 CAHPS_GRP_5 CAHPS for MIPS SSM: Health Promotion and Education
#> 5 CAHPS_GRP_8 CAHPS for MIPS SSM: Courteous and Helpful Office Staff
#> 6 CAHPS_GRP_12 CAHPS for MIPS SSM: Stewardship of Patient Resources
cms_patient_experience %>%
pivot_wider(
id_cols = starts_with("org"),
names_from = measure_cd,
values_from = prf_rate
)
#> # A tibble: 95 × 8
#> org_pac_id org_nm CAHPS…¹ CAHPS…² CAHPS…³ CAHPS…⁴ CAHPS…⁵ CAHPS…⁶
#> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 0446157747 USC CARE ME… 63 87 86 57 85 24
#> 2 0446162697 ASSOCIATION… 59 85 83 63 88 22
#> 3 0547164295 BEAVER MEDI… 49 NA 75 44 73 12
#> 4 0749333730 CAPE PHYSIC… 67 84 85 65 82 24
#> 5 0840104360 ALLIANCE PH… 66 87 87 64 87 28
#> 6 0840109864 REX HOSPITA… 73 87 84 67 91 30
#> 7 0840513552 SCL HEALTH … 58 83 76 58 78 26
#> 8 0941545784 GRITMAN MED… 46 86 81 54 NA 25
#> 9 1052612785 COMMUNITY M… 65 84 80 58 87 29
#> 10 1254237779 OUR LADY OF… 61 NA NA 65 NA 17
#> # … with 85 more rows, and abbreviated variable names ¹CAHPS_GRP_1,
#> # ²CAHPS_GRP_2, ³CAHPS_GRP_3, ⁴CAHPS_GRP_5, ⁵CAHPS_GRP_8, ⁶CAHPS_GRP_12
cms_patient_care %>%
pivot_wider(
names_from = type,
values_from = score
)
#> # A tibble: 126 × 5
#> ccn facility_name measure_…¹ denom…² obser…³
#> <chr> <chr> <chr> <dbl> <dbl>
#> 1 011500 BAPTIST HOSPICE beliefs_a… 202 100
#> 2 011500 BAPTIST HOSPICE composite… 202 88.1
#> 3 011500 BAPTIST HOSPICE dyspena_t… 110 99.1
#> 4 011500 BAPTIST HOSPICE dyspnea_s… 202 100
#> 5 011500 BAPTIST HOSPICE opioid_bo… 61 100
#> 6 011500 BAPTIST HOSPICE pain_asse… 107 100
#> 7 011500 BAPTIST HOSPICE pain_scre… 202 88.6
#> 8 011500 BAPTIST HOSPICE treat_pref 202 100
#> 9 011500 BAPTIST HOSPICE visits_im… 232 96.1
#> 10 011501 SOUTHERNCARE NEW BEACON N. BIRMINGHAM beliefs_a… 525 100
#> # … with 116 more rows, and abbreviated variable names ¹measure_abbr,
#> # ²denominator, ³observed
cms_patient_care %>%
pivot_wider(
names_from = measure_abbr,
values_from = score
)
#> # A tibble: 28 × 12
#> ccn facility…¹ type belie…² compo…³ dyspe…⁴ dyspn…⁵ opioi…⁶ pain_…⁷
#> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 011500 BAPTIST H… deno… 202 202 110 202 61 107
#> 2 011500 BAPTIST H… obse… 100 88.1 99.1 100 100 100
#> 3 011501 SOUTHERNC… deno… 525 525 438 525 101 325
#> 4 011501 SOUTHERNC… obse… 100 100 100 100 100 100
#> 5 011502 COMFORT C… deno… 295 295 236 295 38 121
#> 6 011502 COMFORT C… obse… 100 99.3 99.2 100 100 100
#> 7 011503 SAAD HOSP… deno… 694 694 555 694 37 677
#> 8 011503 SAAD HOSP… obse… 99.9 96 99.6 98.3 100 99
#> 9 011505 HOSPICE F… deno… 600 600 308 600 151 308
#> 10 011505 HOSPICE F… obse… 97.8 92 97.7 99.8 98.7 92.5
#> # … with 18 more rows, 3 more variables: pain_screening <dbl>,
#> # treat_pref <dbl>, visits_imminent <dbl>, and abbreviated variable
#> # names ¹facility_name, ²beliefs_addressed, ³composite_process,
#> # ⁴dyspena_treatment, ⁵dyspnea_screening, ⁶opioid_bowel,
#> # ⁷pain_assessment
cms_patient_care %>%
pivot_wider(
names_from = c(measure_abbr, type),
values_from = score
)
#> # A tibble: 14 × 20
#> ccn facili…¹ belie…² belie…³ compo…⁴ compo…⁵ dyspe…⁶ dyspe…⁷ dyspn…⁸
#> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 011500 BAPTIST… 202 100 202 88.1 110 99.1 202
#> 2 011501 SOUTHER… 525 100 525 100 438 100 525
#> 3 011502 COMFORT… 295 100 295 99.3 236 99.2 295
#> 4 011503 SAAD HO… 694 99.9 694 96 555 99.6 694
#> 5 011505 HOSPICE… 600 97.8 600 92 308 97.7 600
#> 6 011506 SOUTHER… 589 100 589 99.7 477 100 589
#> 7 011508 SOUTHER… 420 100 420 99.5 347 100 420
#> 8 011510 CULLMAN… 54 100 54 90.7 27 100 54
#> 9 011511 HOSPICE… 179 100 179 99.4 123 99.2 179
#> 10 011512 SOUTHER… 396 100 396 99.5 241 100 396
#> 11 011513 SHEPHER… 335 99.1 335 87.2 154 90.9 335
#> 12 011514 ST VINC… 210 100 210 97.6 137 100 210
#> 13 011516 HOSPICE… 103 100 103 97.1 75 98.7 103
#> 14 011517 HOSPICE… 400 99.8 400 95.8 182 99.5 400
#> # … with 11 more variables: dyspnea_screening_observed <dbl>,
#> # opioid_bowel_denominator <dbl>, opioid_bowel_observed <dbl>,
#> # pain_assessment_denominator <dbl>, pain_assessment_observed <dbl>,
#> # pain_screening_denominator <dbl>, pain_screening_observed <dbl>,
#> # treat_pref_denominator <dbl>, treat_pref_observed <dbl>,
#> # visits_imminent_denominator <dbl>, visits_imminent_observed <dbl>,
#> # and abbreviated variable names ¹facility_name, …
相关用法
- R tidyr chop 砍伐和砍伐
- R tidyr complete 完成缺少数据组合的 DataFrame
- R tidyr separate_rows 将折叠的列分成多行
- R tidyr extract 使用正则表达式组将字符列提取为多列
- R tidyr pivot_longer_spec 使用规范将数据从宽转为长
- R tidyr unnest_longer 将列表列取消嵌套到行中
- R tidyr uncount “计数” DataFrame
- R tidyr pivot_wider_spec 使用规范将数据从长轴转向宽轴
- R tidyr replace_na 将 NA 替换为指定值
- R tidyr unnest_wider 将列表列取消嵌套到列中
- R tidyr full_seq 在向量中创建完整的值序列
- R tidyr nest 将行嵌套到 DataFrame 的列表列中
- R tidyr separate 使用正则表达式或数字位置将字符列分成多列
- R tidyr pivot_wider 将数据从长轴转向宽轴
- R tidyr nest_legacy Nest() 和 unnest() 的旧版本
- R tidyr separate_longer_delim 将字符串拆分为行
- R tidyr gather 将列收集到键值对中
- R tidyr hoist 将值提升到列表列之外
- R tidyr pivot_longer 将数据从宽转为长
- R tidyr pack 打包和拆包
- R tidyr separate_wider_delim 将字符串拆分为列
- R tidyr drop_na 删除包含缺失值的行
- R tidyr fill 用上一个或下一个值填充缺失值
- R tidyr tidyr_legacy 旧名称修复
- R tidyr expand 扩展 DataFrame 以包含所有可能的值组合
注：本文由纯净天空筛选整理自Hadley Wickham等大神的英文原创作品 Data from the Centers for Medicare & Medicaid Services。非经特殊声明，原始代码版权归原作者所有，本译文未经允许或授权，请勿转载或复制。