saturn·

← all readings

healthcare cms hospitals 2025

saturn notebook · generated 2026-05-01 Report Notebook

Overview

Source: /home/coolhand/datasets/us-inequality-atlas/healthcare/cms_hospitals_2025.csv

Saturn profiled 5,421 rows across 38 columns. The stats below are deterministic and machine-readable; the prose is a language-model interpretation of those stats (opt-in, added after the fact, never sees raw rows).

[2]:
!pip install saturn-dissect
import subprocess
subprocess.run([
    "saturn", "analyze", "/home/coolhand/datasets/us-inequality-atlas/healthcare/cms_hospitals_2025.csv",
    "--findings", "healthcare-cms_hospitals_2025.json",
    "--llm", "anthropic:claude-opus-4-7",
])

Summary confidence: high

This dataset is a CMS hospital directory covering 5,421 U.S. hospitals across 56 state/territory codes, with 38 columns mixing facility identifiers (Facility ID, Name, Address, Phone), location fields, and a battery of CMS quality-measure summaries (Mortality, Readmission, Safety, Patient Experience, Timely & Effective care). Two things are worth a closer look first: the Hospital overall rating is 'Not Available' for 47% of facilities, and the 'Meets criteria for birthing friendly designation' field is 58% null with only 'Y' as a value, so any rating- or designation-based analysis will be heavily gated by missingness. Beyond that, the mix is dominated by Acute Care Hospitals (3,120) and Voluntary non-profit – Private ownership (2,291 / ~42%), with Texas, California, and Florida holding the largest state shares. The 'Count of … Measures Worse/Better' fields are highly skewed toward 0, suggesting most hospitals look 'no different than national average' on CMS comparisons — a useful framing before drilling into outliers.

citing: row_count · column_count · Hospital overall rating · Meets criteria for birthing friendly designation · Hospital Type · Hospital Ownership · State · Emergency Services · Count of MORT Measures Worse · Count of READM Measures Better

Out[4]:

saturn.schema() · 38 columns

column kind n null% unique alerts
Facility ID text 5,421 0.0% 5,421 near_unique one_word allcaps short_text
Facility Name text 5,421 0.0% 5,286 near_unique allcaps
Address text 5,421 0.0% 5,387 near_unique allcaps
City/Town text 5,421 0.0% 3,049 one_word allcaps short_text duplicates
State categorical 5,421 0.0% 56
ZIP Code numeric 5,421 0.0% 4,721
County/Parish text 5,421 0.0% 1,555 one_word allcaps short_text duplicates
Telephone Number text 5,421 0.0% 5,383 near_unique allcaps short_text
Hospital Type categorical 5,421 0.0% 8
Hospital Ownership categorical 5,421 0.0% 12
Emergency Services categorical 5,421 0.0% 2
Meets criteria for birthing friendly designation categorical 5,421 58.2% 1 null_rate imbalance
Hospital overall rating categorical 5,421 0.0% 6
Hospital overall rating footnote categorical 5,421 52.7% 7 null_rate
MORT Group Measure Count categorical 5,421 0.0% 2
Count of Facility MORT Measures categorical 5,421 0.0% 8
Count of MORT Measures Better categorical 5,421 0.0% 9
Count of MORT Measures No Different categorical 5,421 0.0% 9
Count of MORT Measures Worse categorical 5,421 0.0% 7
MORT Group Footnote numeric 5,421 67.2% 4 null_rate
Safety Group Measure Count categorical 5,421 0.0% 2
Count of Facility Safety Measures categorical 5,421 0.0% 9
Count of Safety Measures Better categorical 5,421 0.0% 8
Count of Safety Measures No Different categorical 5,421 0.0% 10
Count of Safety Measures Worse categorical 5,421 0.0% 5
Safety Group Footnote numeric 5,421 61.8% 4 null_rate
READM Group Measure Count categorical 5,421 0.0% 2
Count of Facility READM Measures categorical 5,421 0.0% 12
Count of READM Measures Better categorical 5,421 0.0% 7
Count of READM Measures No Different categorical 5,421 0.0% 13
Count of READM Measures Worse categorical 5,421 0.0% 9
READM Group Footnote numeric 5,421 78.8% 3 null_rate
Pt Exp Group Measure Count categorical 5,421 0.0% 2
Count of Facility Pt Exp Measures categorical 5,421 0.0% 2
Pt Exp Group Footnote numeric 5,421 58.2% 3 null_rate
TE Group Measure Count categorical 5,421 0.0% 2
Count of Facility TE Measures categorical 5,421 0.0% 13
TE Group Footnote numeric 5,421 82.9% 3 null_rate high_skew outliers
Fig 1.
Hospital overall rating · Distribution of CMS star ratings — note that 'Not Available' is the single largest bucket (47%).
Show data table
valuecountshare
Not Available255247.1%
393717.3%
476514.1%
264912.0%
52895.3%
12294.2%
Fig 2.
Hospital Type · Acute Care Hospitals dominate at ~58%, with Critical Access and Psychiatric making up most of the remainder.
Show data table
valuecountshare
Acute Care Hospitals312057.6%
Critical Access Hospitals137525.4%
Psychiatric62611.5%
Acute Care - Veterans Administration1322.4%
Childrens941.7%
Rural Emergency Hospital380.7%
Acute Care - Department of Defense320.6%
Long-term40.1%
Fig 3.
Hospital Ownership · Voluntary non-profit Private leads at ~42%; useful for segmenting quality outcomes by ownership model.
Show data table
valuecountshare
Voluntary non-profit - Private229142.3%
Proprietary106719.7%
Government - Hospital District or Authority5219.6%
Government - Local4007.4%
Voluntary non-profit - Other3616.7%
Voluntary non-profit - Church2755.1%
Government - State2103.9%
Veterans Health Administration1322.4%
Physician741.4%
Government - Federal440.8%
Department of Defense320.6%
Tribal140.3%
Fig 4.
State · Hospital counts by state — TX, CA, and FL top the list; helpful for normalizing any state-level comparisons.
Show data table
valuecountshare
TX4628.5%
CA3787.0%
FL2214.1%
IL1943.6%
OH1943.6%
NY1913.5%
PA1873.4%
LA1603.0%
GA1492.7%
IN1492.7%
MI1472.7%
WI1422.6%
KS1392.6%
MN1362.5%
OK1352.5%
TN1232.3%
MO1212.2%
NC1202.2%
IA1182.2%
AZ1062.0%
Fig 5.
Emergency Services · 83% of facilities offer emergency services, a quick sanity check on facility mix before quality analysis.
Show data table
valuecountshare
Yes450583.1%
No91616.9%
Fig 6.
Per-column null rate across the corpus. Columns are ordered by input position.
Show data table
columnkindnull %
Facility IDtext0.0%
Facility Nametext0.0%
Addresstext0.0%
City/Towntext0.0%
Statecategorical0.0%
ZIP Codenumeric0.0%
County/Parishtext0.0%
Telephone Numbertext0.0%
Hospital Typecategorical0.0%
Hospital Ownershipcategorical0.0%
Emergency Servicescategorical0.0%
Meets criteria for birthing friendly designationcategorical58.2%
Hospital overall ratingcategorical0.0%
Hospital overall rating footnotecategorical52.7%
MORT Group Measure Countcategorical0.0%
Count of Facility MORT Measurescategorical0.0%
Count of MORT Measures Bettercategorical0.0%
Count of MORT Measures No Differentcategorical0.0%
Count of MORT Measures Worsecategorical0.0%
MORT Group Footnotenumeric67.2%
Safety Group Measure Countcategorical0.0%
Count of Facility Safety Measurescategorical0.0%
Count of Safety Measures Bettercategorical0.0%
Count of Safety Measures No Differentcategorical0.0%
Count of Safety Measures Worsecategorical0.0%
Safety Group Footnotenumeric61.8%
READM Group Measure Countcategorical0.0%
Count of Facility READM Measurescategorical0.0%
Count of READM Measures Bettercategorical0.0%
Count of READM Measures No Differentcategorical0.0%
Count of READM Measures Worsecategorical0.0%
READM Group Footnotenumeric78.8%
Pt Exp Group Measure Countcategorical0.0%
Count of Facility Pt Exp Measurescategorical0.0%
Pt Exp Group Footnotenumeric58.2%
TE Group Measure Countcategorical0.0%
Count of Facility TE Measurescategorical0.0%
TE Group Footnotenumeric82.9%
Fig 7.
Pearson correlation across numeric columns (sampled, bounded).
Show data table
ZIP CodeMORT Group FootnoteSafety Group FootnoteREADM Group FootnotePt Exp Group FootnoteTE Group Footnote
ZIP Code+1.00-0.01-0.04-0.09-0.02+0.03
MORT Group Footnote-0.01+1.00+0.13+0.24+0.07+0.09
Safety Group Footnote-0.04+0.13+1.00+0.10+0.27-0.00
READM Group Footnote-0.09+0.24+0.10+1.00+0.06+0.07
Pt Exp Group Footnote-0.02+0.07+0.27+0.06+1.00+0.03
TE Group Footnote+0.03+0.09-0.00+0.07+0.03+1.00

Facility ID text identifier

Facility ID is a fixed-width 6-character single-token code, unique across all 5421 rows with zero nulls or duplicates. Every value is one word in all caps with length exactly 6, and the sampled tokens (e.g., 010001, 010005) are zero-padded numeric strings consistent with a primary facility identifier.

Treatment: Treat as primary key; left-join on this id and exclude from modelling features.

anthropic:claude-opus-4-7 · confidence high
Out[13]:

saturn.columns["Facility ID"].stats

statvalue
n5,421
nulls0 (0.0%)
unique5,421
len_min 6
len_max 6
len_mean 6
len_median 6
len_p95 6
word_mean 1
word_median 1
n_empty 0
n_duplicates 0
duplicate_rate 0
vocab_size 5,421
readability_flesch_mean 121.2
emoji_rate 0
url_rate 0
one_word_rate 1
allcaps_rate 1
boilerplate_rate 0
alert: near_unique100.0% of rows are unique strings
alert: one_word100.0% rows are a single word
alert: allcaps100.0% rows are all-caps
alert: short_text95th-percentile length under 20 chars
Fig 8.
Character-length distribution for Facility ID.
Show data table
charscount
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 65421
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60
6 – 60

Facility Name text identifier

This column holds names of healthcare facilities, dominated by terms like 'hospital' (2740), 'center' (1579), and 'medical' (1444), with a typical length of 4 words / 28 characters. Values are near-unique (5286 distinct out of 5421) yet 135 duplicates remain, suggesting either multi-site chains or repeated reporting rows for the same facility. Nearly everything is uppercase (99.3% allcaps rate), which will trip case-sensitive joins.

Treatment: Normalize case and whitespace before using as a join key on facility.

anthropic:claude-opus-4-7 · confidence high
Out[16]:

saturn.columns["Facility Name"].stats

statvalue
n5,421
nulls0 (0.0%)
unique5,286
len_min 3
len_max 74
len_mean 29.21
len_median 28
len_p95 45
word_mean 3.995
word_median 4
n_empty 0
n_duplicates 135
duplicate_rate 0.0249
vocab_size 3,942
readability_flesch_mean 6.842
emoji_rate 0
url_rate 0
one_word_rate 0.001845
allcaps_rate 0.9932
boilerplate_rate 0
alert: near_unique97.5% of rows are unique strings
alert: allcaps99.3% rows are all-caps
Fig 9.
Character-length distribution for Facility Name.
Show data table
charscount
3 – 52
5 – 71
7 – 81
8 – 1011
10 – 1212
12 – 1443
14 – 1591
15 – 17178
17 – 1993
19 – 21258
21 – 23424
23 – 24526
24 – 26572
26 – 28258
28 – 30548
30 – 31525
31 – 33460
33 – 35160
35 – 37308
37 – 38232
38 – 40170
40 – 42149
42 – 4447
44 – 46105
46 – 4782
47 – 4979
49 – 5155
51 – 537
53 – 544
54 – 562
56 – 581
58 – 603
60 – 624
62 – 631
63 – 652
65 – 671
67 – 692
69 – 700
70 – 723
72 – 741

Address text identifier

Free-text street addresses, with 5387 unique values across 5421 rows (near-unique) and no nulls. 99.2% are all-caps and the top tokens are 'street', 'st', 'avenue', 'drive', 'road', confirming postal-style entries averaging 3.75 words and 19 characters. 34 duplicates exist but no boilerplate, URLs, or emoji.

Treatment: Drop or geocode/parse into structured components before modelling; do not feed raw.

anthropic:claude-opus-4-7 · confidence high
Out[19]:

saturn.columns["Address"].stats

statvalue
n5,421
nulls0 (0.0%)
unique5,387
len_min 7
len_max 50
len_mean 19.37
len_median 19
len_p95 29
word_mean 3.754
word_median 4
n_empty 0
n_duplicates 34
duplicate_rate 0.006272
vocab_size 4,996
readability_flesch_mean 79.27
emoji_rate 0
url_rate 0
one_word_rate 0
allcaps_rate 0.9921
boilerplate_rate 0
alert: near_unique99.4% of rows are unique strings
alert: allcaps99.2% rows are all-caps
Fig 10.
Character-length distribution for Address.
Show data table
charscount
7 – 83
8 – 98
9 – 1032
10 – 1166
11 – 12115
12 – 13227
13 – 15288
15 – 16380
16 – 17481
17 – 18502
18 – 19541
19 – 20510
20 – 21413
21 – 22691
22 – 23257
23 – 24218
24 – 25151
25 – 26121
26 – 2773
27 – 2872
28 – 3052
30 – 3147
31 – 3234
32 – 3327
33 – 3415
34 – 3512
35 – 3634
36 – 3712
37 – 388
38 – 397
39 – 406
40 – 413
41 – 422
42 – 443
44 – 450
45 – 463
46 – 472
47 – 480
48 – 490
49 – 505

City/Town text feature

This is a US city/town name field, almost entirely uppercased (allcaps_rate 0.994) and dominated by single-word entries (one_word_rate 0.771, word_mean 1.24). Of 5421 rows there are 3049 unique values with a 0.438 duplicate rate, led by CHICAGO (34), HOUSTON (31), and COLUMBUS (23). Lengths are short and tight (len_mean 8.6, len_max 24) and there are no nulls or empties.

Treatment: Normalize case and standardize against a city gazetteer (ideally with state) before grouping or joining.

anthropic:claude-opus-4-7 · confidence high
Out[22]:

saturn.columns["City/Town"].stats

statvalue
n5,421
nulls0 (0.0%)
unique3,049
len_min 3
len_max 24
len_mean 8.611
len_median 8
len_p95 13
word_mean 1.241
word_median 1
n_empty 0
n_duplicates 2,372
duplicate_rate 0.4376
vocab_size 2,890
readability_flesch_mean 18.29
emoji_rate 0
url_rate 0
one_word_rate 0.7709
allcaps_rate 0.9943
boilerplate_rate 0
alert: one_word77.1% rows are a single word
alert: allcaps99.4% rows are all-caps
alert: short_text95th-percentile length under 20 chars
alert: duplicates43.8% duplicate strings
Fig 11.
Character-length distribution for City/Town.
Show data table
charscount
3 – 410
4 – 4122
4 – 50
5 – 5332
5 – 60
6 – 6761
6 – 70
7 – 7895
7 – 80
8 – 8737
8 – 90
9 – 9694
9 – 100
10 – 10705
10 – 110
11 – 11446
11 – 120
12 – 12295
12 – 130
13 – 14191
14 – 1498
14 – 150
15 – 1550
15 – 160
16 – 1654
16 – 170
17 – 1715
17 – 180
18 – 186
18 – 190
19 – 193
19 – 200
20 – 206
20 – 210
21 – 210
21 – 220
22 – 220
22 – 230
23 – 230
23 – 241

State categorical feature

US state codes covering 56 distinct values across 5,421 rows with no nulls — likely all 50 states plus territories/DC. Distribution is broad and near-uniform (entropy ratio 0.917), with TX leading at only 8.5% and CA, FL, IL, OH following. The 56 cardinality is worth noting since it exceeds the standard 50 states.

Treatment: one-hot or target-encode for modelling; optionally group rare territories.

anthropic:claude-opus-4-7 · confidence high
Out[25]:

saturn.columns["State"].stats

statvalue
n5,421
nulls0 (0.0%)
unique56
top_value TX
top_rate 0.08522
cardinality 56
entropy 5.328
entropy_ratio 0.9174
Fig 12.
Top values for State.
Show data table
valuecountshare
TX4628.5%
CA3787.0%
FL2214.1%
IL1943.6%
OH1943.6%
NY1913.5%
PA1873.4%
LA1603.0%
GA1492.7%
IN1492.7%
MI1472.7%
WI1422.6%
KS1392.6%
MN1362.5%
OK1352.5%
TN1232.3%
MO1212.2%
NC1202.2%
IA1182.2%
AZ1062.0%

ZIP Code numeric identifier

This is a US ZIP code field stored as a numeric column, with 4721 unique values across 5421 rows and no nulls. The range (603 to 99929) and broad IQR (32771-76104) are consistent with national ZIP coverage, and leading-zero ZIPs (e.g., the min of 603) have already been corrupted by numeric storage. Treating the mean (53780) or std (27064) as meaningful is misleading since ZIPs are categorical identifiers, not quantities.

Treatment: Cast to zero-padded 5-character strings and treat as a categorical/geographic key rather than a numeric feature.

anthropic:claude-opus-4-7 · confidence high
Out[28]:

saturn.columns["ZIP Code"].stats

statvalue
n5,421
nulls0 (0.0%)
unique4,721
min 603
max 99,929
mean 5.378e+04
median 55,066
std 2.706e+04
q1 32,771
q3 76,104
iqr 43,333
skew -0.1646
kurtosis -0.9879
n_outliers 0
outlier_rate 0
zero_rate 0
Fig 13.
Distribution of ZIP Code. Vertical dash marks the median.
Show data table
bincount
603 – 3086161
3086 – 556973
5569 – 805292
8052 – 1.054e+0457
1.054e+04 – 1.302e+0490
1.302e+04 – 1.55e+04101
1.55e+04 – 1.799e+0481
1.799e+04 – 2.047e+04108
2.047e+04 – 2.295e+0479
2.295e+04 – 2.543e+0481
2.543e+04 – 2.792e+0482
2.792e+04 – 3.04e+04191
3.04e+04 – 3.288e+04171
3.288e+04 – 3.537e+04168
3.537e+04 – 3.785e+04151
3.785e+04 – 4.033e+04180
4.033e+04 – 4.282e+0487
4.282e+04 – 4.53e+04154
4.53e+04 – 4.778e+04174
4.778e+04 – 5.027e+04180
5.027e+04 – 5.275e+0498
5.275e+04 – 5.523e+04160
5.523e+04 – 5.772e+04175
5.772e+04 – 6.02e+04147
6.02e+04 – 6.268e+04140
6.268e+04 – 6.516e+04120
6.516e+04 – 6.765e+04133
6.765e+04 – 7.013e+04145
7.013e+04 – 7.261e+04205
7.261e+04 – 7.51e+04191
7.51e+04 – 7.758e+04236
7.758e+04 – 8.006e+04204
8.006e+04 – 8.255e+04103
8.255e+04 – 8.503e+04132
8.503e+04 – 8.751e+04106
8.751e+04 – 9e+0472
9e+04 – 9.248e+04140
9.248e+04 – 9.496e+04146
9.496e+04 – 9.745e+04159
9.745e+04 – 9.993e+04148

County/Parish text feature

This column holds U.S. county or parish names, stored uppercase and almost always as a single token (one_word_rate 0.87, allcaps_rate 1.0). With 1,555 uniques across 5,421 rows and a 71.3% duplicate rate, common counties repeat heavily — LOS ANGELES (88), JEFFERSON and COOK (59 each) lead. Note that vocab_size (1591) exceeds n_unique (1555), implying multi-word names like SAN/LOS/ST. variants contribute extra tokens.

Treatment: Normalize casing and join to a state column before using as a categorical geographic feature.

anthropic:claude-opus-4-7 · confidence high
Out[31]:

saturn.columns["County/Parish"].stats

statvalue
n5,421
nulls0 (0.0%)
unique1,555
len_min 3
len_max 25
len_mean 7.34
len_median 7
len_p95 11
word_mean 1.135
word_median 1
n_empty 0
n_duplicates 3,866
duplicate_rate 0.7132
vocab_size 1,591
readability_flesch_mean 34.44
emoji_rate 0
url_rate 0
one_word_rate 0.8733
allcaps_rate 1
boilerplate_rate 0
alert: one_word87.3% rows are a single word
alert: allcaps100.0% rows are all-caps
alert: short_text95th-percentile length under 20 chars
alert: duplicates71.3% duplicate strings
Fig 14.
Character-length distribution for County/Parish.
Show data table
charscount
3 – 436
4 – 4472
4 – 50
5 – 5659
5 – 60
6 – 61008
6 – 70
7 – 7956
7 – 80
8 – 8834
8 – 9575
9 – 100
10 – 10430
10 – 110
11 – 11195
11 – 120
12 – 12101
12 – 130
13 – 1340
13 – 140
14 – 1575
15 – 1518
15 – 160
16 – 162
16 – 170
17 – 175
17 – 180
18 – 183
18 – 190
19 – 205
20 – 204
20 – 210
21 – 211
21 – 220
22 – 220
22 – 230
23 – 231
23 – 240
24 – 240
24 – 251

Telephone Number text identifier

This column holds US-style telephone numbers, every value exactly 14 characters long with a mean of 2 words, consistent with a `(NPA) NNN-NNNN` format. Of 5421 rows, 5383 are unique and 38 duplicates appear (0.7%), with no nulls; the most common tokens are area codes like (406), (605), and (402). The near-unique cardinality and rigid length make this an identifier rather than a feature.

Treatment: Drop for modelling; retain as a contact identifier or parse out the area code if geography is useful.

anthropic:claude-opus-4-7 · confidence high
Out[34]:

saturn.columns["Telephone Number"].stats

statvalue
n5,421
nulls0 (0.0%)
unique5,383
len_min 14
len_max 14
len_mean 14
len_median 14
len_p95 14
word_mean 2
word_median 2
n_empty 0
n_duplicates 38
duplicate_rate 0.00701
vocab_size 5,550
readability_flesch_mean 120.2
emoji_rate 0
url_rate 0
one_word_rate 0
allcaps_rate 1
boilerplate_rate 0
alert: near_unique99.3% of rows are unique strings
alert: allcaps100.0% rows are all-caps
alert: short_text95th-percentile length under 20 chars
Fig 15.
Character-length distribution for Telephone Number.
Show data table
charscount
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 145421
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140
14 – 140

Hospital Type categorical feature

Categorical classifier of hospital facilities across 8 types, with no nulls in 5421 rows. Acute Care Hospitals dominate at 57.6% (3120 records), followed by Critical Access (1375) and Psychiatric (626); the long tail is sparse, with only 4 Long-term facilities. Entropy ratio of 0.55 confirms the distribution is heavily concentrated in the top category.

Treatment: One-hot encode, optionally collapsing the four rarest types into an 'Other' bucket.

anthropic:claude-opus-4-7 · confidence high
Out[37]:

saturn.columns["Hospital Type"].stats

statvalue
n5,421
nulls0 (0.0%)
unique8
top_value Acute Care Hospitals
top_rate 0.5755
cardinality 8
entropy 1.654
entropy_ratio 0.5513
Fig 16.
Top values for Hospital Type.
Show data table
valuecountshare
Acute Care Hospitals312057.6%
Critical Access Hospitals137525.4%
Psychiatric62611.5%
Acute Care - Veterans Administration1322.4%
Childrens941.7%
Rural Emergency Hospital380.7%
Acute Care - Department of Defense320.6%
Long-term40.1%

Hospital Ownership categorical feature

Categorical descriptor of hospital ownership type across 5421 records, with 12 distinct categories and no nulls. Distribution is dominated by 'Voluntary non-profit - Private' at 42.26% of rows, followed by 'Proprietary' at 1067 and a long tail down to 'Government - Federal' at 44. Entropy ratio of 0.72 indicates moderate concentration but reasonable spread across the taxonomy.

Treatment: One-hot or target-encode for modelling; consider collapsing rare tiers like 'Physician' and 'Government - Federal'.

anthropic:claude-opus-4-7 · confidence high
Out[40]:

saturn.columns["Hospital Ownership"].stats

statvalue
n5,421
nulls0 (0.0%)
unique12
top_value Voluntary non-profit - Private
top_rate 0.4226
cardinality 12
entropy 2.586
entropy_ratio 0.7215
Fig 17.
Top values for Hospital Ownership.
Show data table
valuecountshare
Voluntary non-profit - Private229142.3%
Proprietary106719.7%
Government - Hospital District or Authority5219.6%
Government - Local4007.4%
Voluntary non-profit - Other3616.7%
Voluntary non-profit - Church2755.1%
Government - State2103.9%
Veterans Health Administration1322.4%
Physician741.4%
Government - Federal440.8%
Department of Defense320.6%
Tribal140.3%

Emergency Services categorical feature

Binary Yes/No flag indicating whether emergency services were involved or available, with no nulls across 5421 rows. The distribution is imbalanced: 'Yes' accounts for 83.1% (4505) versus 916 'No' responses, giving an entropy ratio of 0.655.

Treatment: Encode as a binary 0/1 indicator; be mindful of class imbalance if used as a target.

anthropic:claude-opus-4-7 · confidence high
Out[43]:

saturn.columns["Emergency Services"].stats

statvalue
n5,421
nulls0 (0.0%)
unique2
top_value Yes
top_rate 0.831
cardinality 2
entropy 0.6553
entropy_ratio 0.6553
Fig 18.
Top values for Emergency Services.
Show data table
valuecountshare
Yes450583.1%
No91616.9%

Meets criteria for birthing friendly designation categorical feature

This appears to be a binary flag indicating whether a hospital meets criteria for a 'birthing friendly' designation, but it functions as a presence indicator only. Of 5421 rows, 58.24% are null and the remaining 2264 are all 'Y' — there are no 'N' values, giving cardinality 1 and zero entropy. Nulls effectively mean 'not designated' rather than missing data.

Treatment: Recode nulls as 'N' to form a usable binary indicator, or drop since it carries the same information as the null mask.

anthropic:claude-opus-4-7 · confidence high
Out[46]:

saturn.columns["Meets criteria for birthing friendly designation"].stats

statvalue
n5,421
nulls3,157 (58.2%)
unique1
top_value Y
top_rate 1
cardinality 1
entropy 0
entropy_ratio 0
alert: null_rate58.2% null
alert: imbalancetop value is 100.0% of rows
Fig 19.
Top values for Meets criteria for birthing friendly designation.
Show data table
valuecountshare
Y226441.8%

Hospital overall rating categorical label

This is the CMS-style 1-5 hospital star rating stored as a string, with a sixth bucket 'Not Available' for unrated facilities. The striking issue is that 'Not Available' dominates at 47.1% of 5,421 rows, outnumbering every actual rating; among rated hospitals, 3 stars (937) is most common and 1 star (229) least. Entropy ratio of 0.83 across 6 categories confirms the distribution is spread but heavily anchored by missingness-as-category.

Treatment: Recode 'Not Available' to NaN and treat the remainder as an ordinal 1-5 scale.

anthropic:claude-opus-4-7 · confidence high
Out[49]:

saturn.columns["Hospital overall rating"].stats

statvalue
n5,421
nulls0 (0.0%)
unique6
top_value Not Available
top_rate 0.4708
cardinality 6
entropy 2.133
entropy_ratio 0.8252
Fig 20.
Top values for Hospital overall rating.
Show data table
valuecountshare
Not Available255247.1%
393717.3%
476514.1%
264912.0%
52895.3%
12294.2%

Hospital overall rating footnote categorical metadata

Footnote codes attached to the Hospital overall rating, with only 7 distinct values across 5,421 rows. Over half the column is null (null_rate 0.527), and among populated rows code '16' dominates at 65.4% followed by '19', so the field carries low information (entropy_ratio 0.41). One compound entry '16, 23' appears twice, indicating values can be multi-coded.

Treatment: Keep as a categorical flag alongside the rating; split the rare compound codes if you need per-footnote analysis.

anthropic:claude-opus-4-7 · confidence high
Out[52]:

saturn.columns["Hospital overall rating footnote"].stats

statvalue
n5,421
nulls2,857 (52.7%)
unique7
top_value 16
top_rate 0.6537
cardinality 7
entropy 1.158
entropy_ratio 0.4126
alert: null_rate52.7% null
Fig 21.
Top values for Hospital overall rating footnote.
Show data table
valuecountshare
16167630.9%
1979514.7%
5470.9%
22320.6%
1770.1%
2350.1%
16, 2320.0%

MORT Group Measure Count categorical feature

This is a binary categorical field indicating the count of measures in a mortality (MORT) group, holding only the value '7' (84.1% of rows) or 'Not Available' (the remaining 863 rows). Despite being labeled a count, it functions as a presence flag: when data exists, the count is always 7. No nulls are recorded, since missingness is encoded as the literal string 'Not Available'.

Treatment: Recode to a boolean availability flag ('7' vs 'Not Available') before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[55]:

saturn.columns["MORT Group Measure Count"].stats

statvalue
n5,421
nulls0 (0.0%)
unique2
top_value 7
top_rate 0.8408
cardinality 2
entropy 0.6324
entropy_ratio 0.6324
Fig 22.
Top values for MORT Group Measure Count.
Show data table
valuecountshare
7455884.1%
Not Available86315.9%

Count of Facility MORT Measures categorical feature

Likely the count of facility mortality (MORT) measures reported per hospital, stored as strings 1-7 alongside a 'Not Available' sentinel. The dominant value is 'Not Available' at 32.8% (1777/5421), which makes the column nominally categorical with 8 levels even though 7 of them are integers. Entropy ratio of 0.92 indicates the non-null counts are spread fairly evenly across 1-7.

Treatment: Replace 'Not Available' with NaN, cast remaining values to integer, and optionally add a missingness indicator.

anthropic:claude-opus-4-7 · confidence high
Out[58]:

saturn.columns["Count of Facility MORT Measures"].stats

statvalue
n5,421
nulls0 (0.0%)
unique8
top_value Not Available
top_rate 0.3278
cardinality 8
entropy 2.765
entropy_ratio 0.9217
Fig 23.
Top values for Count of Facility MORT Measures.
Show data table
valuecountshare
Not Available177732.8%
785015.7%
658710.8%
14959.1%
54558.4%
34448.2%
24207.7%
43937.2%

Count of MORT Measures Better categorical feature

Categorical count of mortality measures on which a hospital performed better than the national rate, encoded as small integers stored as strings (0–7) plus a 'Not Available' sentinel. The distribution is heavily concentrated at 0 (57.8% of 5421 rows) with another 1777 rows marked 'Not Available', leaving only ~10% of hospitals showing any 'better' measure. Entropy ratio of 0.458 confirms the skew, and the sentinel string blocks direct numeric use.

Treatment: Replace 'Not Available' with NaN, cast remaining values to int, and consider binarising (any-better vs none) given the skew.

anthropic:claude-opus-4-7 · confidence high
Out[61]:

saturn.columns["Count of MORT Measures Better"].stats

statvalue
n5,421
nulls0 (0.0%)
unique9
top_value 0
top_rate 0.5785
cardinality 9
entropy 1.453
entropy_ratio 0.4583
Fig 24.
Top values for Count of MORT Measures Better.
Show data table
valuecountshare
0313657.8%
Not Available177732.8%
12975.5%
21332.5%
3531.0%
4150.3%
570.1%
720.0%
610.0%

Count of MORT Measures No Different categorical feature

This column counts how many mortality (MORT) measures a hospital scored 'No Different' on, encoded as a small integer 0-7 but stored as strings alongside a 'Not Available' sentinel. Cardinality is just 9 with high entropy ratio (0.885), meaning values are spread fairly evenly across the integers — except 'Not Available' dominates at 32.8% (1777/5421) and '0' is rare at only 12 rows. Analysts should note the heavy missing-as-string encoding and the near-empty '0' bucket.

Treatment: Recode 'Not Available' to null and cast remaining values to integer before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[64]:

saturn.columns["Count of MORT Measures No Different"].stats

statvalue
n5,421
nulls0 (0.0%)
unique9
top_value Not Available
top_rate 0.3278
cardinality 9
entropy 2.806
entropy_ratio 0.8852
Fig 25.
Top values for Count of MORT Measures No Different.
Show data table
valuecountshare
Not Available177732.8%
667212.4%
554110.0%
15139.5%
35099.4%
45039.3%
24728.7%
74227.8%
0120.2%

Count of MORT Measures Worse categorical feature

This column counts how many mortality (MORT) measures a hospital scored worse than the national average, encoded as small integers 0-5 with a 'Not Available' sentinel mixed in. Roughly 60% of 5421 rows are '0' and another 1777 are 'Not Available', leaving only 378 hospitals flagged on any MORT measure and just 1 hospital at the maximum of 5. The mixed string/integer encoding is the main gotcha.

Treatment: Replace 'Not Available' with NaN and cast to integer before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[67]:

saturn.columns["Count of MORT Measures Worse"].stats

statvalue
n5,421
nulls0 (0.0%)
unique7
top_value 0
top_rate 0.6025
cardinality 7
entropy 1.294
entropy_ratio 0.4608
Fig 26.
Top values for Count of MORT Measures Worse.
Show data table
valuecountshare
0326660.2%
Not Available177732.8%
13105.7%
2571.1%
370.1%
430.1%
510.0%

MORT Group Footnote numeric metadata

This appears to be a footnote code attached to MORT (mortality) group records, stored as a small numeric category with only 4 distinct values ranging from 5 to 23. Two-thirds of rows are null (null_rate 0.672), suggesting the footnote applies only to a minority of records. The strongly negative kurtosis (-1.96) and bimodal-looking quartiles (Q1=5, Q3=19) confirm these are discrete codes rather than a continuous measurement.

Treatment: Cast to categorical and treat nulls as 'no footnote' rather than imputing numerically.

anthropic:claude-opus-4-7 · confidence high
Out[70]:

saturn.columns["MORT Group Footnote"].stats

statvalue
n5,421
nulls3,643 (67.2%)
unique4
min 5
max 23
mean 11.58
median 5
std 7.057
q1 5
q3 19
iqr 14
skew 0.1488
kurtosis -1.959
n_outliers 0
outlier_rate 0
zero_rate 0
alert: null_rate67.2% null
Fig 27.
Distribution of MORT Group Footnote. Vertical dash marks the median.
Show data table
bincount
5 – 5.45950
5.45 – 5.90
5.9 – 6.350
6.35 – 6.80
6.8 – 7.250
7.25 – 7.70
7.7 – 8.150
8.15 – 8.60
8.6 – 9.050
9.05 – 9.50
9.5 – 9.950
9.95 – 10.40
10.4 – 10.850
10.85 – 11.30
11.3 – 11.750
11.75 – 12.20
12.2 – 12.650
12.65 – 13.10
13.1 – 13.550
13.55 – 140
14 – 14.450
14.45 – 14.90
14.9 – 15.350
15.35 – 15.80
15.8 – 16.250
16.25 – 16.70
16.7 – 17.150
17.15 – 17.60
17.6 – 18.050
18.05 – 18.50
18.5 – 18.950
18.95 – 19.4795
19.4 – 19.850
19.85 – 20.30
20.3 – 20.750
20.75 – 21.20
21.2 – 21.650
21.65 – 22.132
22.1 – 22.550
22.55 – 231

Safety Group Measure Count categorical feature

Binary categorical with only two values across 5421 rows: the literal string "8" (84.1%) and "Not Available" (15.9%). Despite the name suggesting a count, it functions as a flag indicating either a fixed measure count of 8 or missing data encoded as text.

Treatment: Recode "Not Available" to null and binarize, or drop given near-constant value.

anthropic:claude-opus-4-7 · confidence high
Out[73]:

saturn.columns["Safety Group Measure Count"].stats

statvalue
n5,421
nulls0 (0.0%)
unique2
top_value 8
top_rate 0.8408
cardinality 2
entropy 0.6324
entropy_ratio 0.6324
Fig 28.
Top values for Safety Group Measure Count.
Show data table
valuecountshare
8455884.1%
Not Available86315.9%

Count of Facility Safety Measures categorical feature

This column reports the count of facility safety measures, stored as a categorical with 9 distinct values (1-8 plus 'Not Available'). The dominant value is 'Not Available' at 38.1% (2,065 of 5,421 rows), making missingness encoded as a string rather than null. Among reported counts, 7 is most common (733), and the distribution across 1-8 is uneven rather than monotonic.

Treatment: Recode 'Not Available' to null and cast remaining values to integer before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[76]:

saturn.columns["Count of Facility Safety Measures"].stats

statvalue
n5,421
nulls0 (0.0%)
unique9
top_value Not Available
top_rate 0.3809
cardinality 9
entropy 2.753
entropy_ratio 0.8684
Fig 29.
Top values for Count of Facility Safety Measures.
Show data table
valuecountshare
Not Available206538.1%
773313.5%
25199.6%
64608.5%
84538.4%
14438.2%
32905.3%
52354.3%
42234.1%

Count of Safety Measures Better categorical feature

This is a small-integer count (0-6) of safety measures rated 'Better', stored as strings alongside a 'Not Available' sentinel. The sentinel dominates at 38.1% (2065/5421) of rows, and the distribution is heavily right-skewed: 0 and 1 cover 2600 rows while 5 and 6 appear only 14 and 3 times. Cardinality is 8 with entropy ratio 0.70, so most signal sits in the lower bins.

Treatment: Recode 'Not Available' to missing, cast remaining values to integer, and consider binning the sparse 4-6 tail.

anthropic:claude-opus-4-7 · confidence high
Out[79]:

saturn.columns["Count of Safety Measures Better"].stats

statvalue
n5,421
nulls0 (0.0%)
unique8
top_value Not Available
top_rate 0.3809
cardinality 8
entropy 2.11
entropy_ratio 0.7033
Fig 30.
Top values for Count of Safety Measures Better.
Show data table
valuecountshare
Not Available206538.1%
0154828.6%
1105219.4%
24307.9%
32164.0%
4931.7%
5140.3%
630.1%

Count of Safety Measures No Different categorical feature

A small-integer count (0-8) of safety measures rated 'no different', stored as strings alongside a 'Not Available' sentinel. The sentinel dominates at 38.1% of 5421 rows (2065), making it the modal value ahead of any actual count. Among real values, 5, 2, 4, and 1 cluster between 509-656 occurrences while 0 and 8 are rare (20 and 10).

Treatment: Cast numeric levels to int and treat 'Not Available' as an explicit missing indicator before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[82]:

saturn.columns["Count of Safety Measures No Different"].stats

statvalue
n5,421
nulls0 (0.0%)
unique10
top_value Not Available
top_rate 0.3809
cardinality 10
entropy 2.685
entropy_ratio 0.8083
Fig 31.
Top values for Count of Safety Measures No Different.
Show data table
valuecountshare
Not Available206538.1%
565612.1%
255110.2%
45279.7%
15099.4%
64828.9%
34348.0%
71673.1%
0200.4%
8100.2%

Count of Safety Measures Worse categorical feature

This is a low-cardinality count column (5 distinct values) recording how many safety measures got worse, taking integer values 0-3 plus a 'Not Available' sentinel. Most rows (54.3%) are 0 and another 2065 are 'Not Available', leaving only 415 rows with any worsening measures (1-3). The mix of numeric strings and a textual missing-marker means it isn't cleanly numeric as stored.

Treatment: Recode 'Not Available' to NaN and cast to integer before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[85]:

saturn.columns["Count of Safety Measures Worse"].stats

statvalue
n5,421
nulls0 (0.0%)
unique5
top_value 0
top_rate 0.5425
cardinality 5
entropy 1.338
entropy_ratio 0.5764
Fig 32.
Top values for Count of Safety Measures Worse.
Show data table
valuecountshare
0294154.3%
Not Available206538.1%
13656.7%
2440.8%
360.1%

Safety Group Footnote numeric metadata

This appears to be a footnote code column tied to a 'Safety Group' classification, encoded numerically but with only 4 distinct values ranging from 5 to 23. 61.8% of rows are null, suggesting footnotes apply only to a minority of records. The bimodal-looking distribution (median 5, q3 19, kurtosis -1.81) indicates these are categorical flags rather than a true measurement.

Treatment: Cast to categorical and treat nulls as 'no footnote' rather than imputing numerically.

anthropic:claude-opus-4-7 · confidence high
Out[88]:

saturn.columns["Safety Group Footnote"].stats

statvalue
n5,421
nulls3,350 (61.8%)
unique4
min 5
max 23
mean 10.69
median 5
std 6.95
q1 5
q3 19
iqr 14
skew 0.4116
kurtosis -1.809
n_outliers 0
outlier_rate 0
zero_rate 0
alert: null_rate61.8% null
Fig 33.
Distribution of Safety Group Footnote. Vertical dash marks the median.
Show data table
bincount
5 – 5.451238
5.45 – 5.90
5.9 – 6.350
6.35 – 6.80
6.8 – 7.250
7.25 – 7.70
7.7 – 8.150
8.15 – 8.60
8.6 – 9.050
9.05 – 9.50
9.5 – 9.950
9.95 – 10.40
10.4 – 10.850
10.85 – 11.30
11.3 – 11.750
11.75 – 12.20
12.2 – 12.650
12.65 – 13.10
13.1 – 13.550
13.55 – 140
14 – 14.450
14.45 – 14.90
14.9 – 15.350
15.35 – 15.80
15.8 – 16.250
16.25 – 16.70
16.7 – 17.150
17.15 – 17.60
17.6 – 18.050
18.05 – 18.50
18.5 – 18.950
18.95 – 19.4795
19.4 – 19.850
19.85 – 20.30
20.3 – 20.750
20.75 – 21.20
21.2 – 21.650
21.65 – 22.132
22.1 – 22.550
22.55 – 236

READM Group Measure Count categorical metadata

A categorical column with only two distinct values: the count '11' covers 84.1% of 5421 rows, with the remaining 863 rows marked 'Not Available'. Functionally this is a binary availability flag rather than a true count, since '11' is the only numeric value present. The mixing of a numeric string with a sentinel 'Not Available' is the main surprise.

Treatment: Recode to a binary available/not-available indicator before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[91]:

saturn.columns["READM Group Measure Count"].stats

statvalue
n5,421
nulls0 (0.0%)
unique2
top_value 11
top_rate 0.8408
cardinality 2
entropy 0.6324
entropy_ratio 0.6324
Fig 34.
Top values for READM Group Measure Count.
Show data table
valuecountshare
11455884.1%
Not Available86315.9%

Count of Facility READM Measures categorical feature

This column reports the count of facility readmission (READM) measures available per facility, stored as strings rather than integers. With 12 distinct values and entropy ratio 0.965, the values are spread fairly evenly across small integers, but the modal value is the literal string "Not Available" at 21.2% (1150 of 5421 rows), which masks missingness as a category. Numeric values like "11", "8", "6", and "9" dominate the rest.

Treatment: Replace "Not Available" with null and cast to integer before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[94]:

saturn.columns["Count of Facility READM Measures"].stats

statvalue
n5,421
nulls0 (0.0%)
unique12
top_value Not Available
top_rate 0.2121
cardinality 12
entropy 3.459
entropy_ratio 0.965
Fig 35.
Top values for Count of Facility READM Measures.
Show data table
valuecountshare
Not Available115021.2%
114989.2%
84668.6%
64388.1%
94257.8%
33756.9%
23746.9%
73586.6%
53476.4%
43356.2%
103336.1%
13225.9%

Count of READM Measures Better categorical feature

Counts how many readmission measures a hospital scored 'better than national rate' on, encoded as small integers 0-5 with 'Not Available' as a seventh category. The distribution is heavily concentrated at 0 (61.5% of 5421 rows) and ties off rapidly: only 28 rows hit 3, 10 hit 4, and 3 hit 5. Notably, 'Not Available' (1150 rows) is the second most common value, larger than every nonzero count combined.

Treatment: Cast numeric levels to int and treat 'Not Available' as an explicit missing-category flag before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[97]:

saturn.columns["Count of READM Measures Better"].stats

statvalue
n5,421
nulls0 (0.0%)
unique7
top_value 0
top_rate 0.6146
cardinality 7
entropy 1.51
entropy_ratio 0.5379
Fig 36.
Top values for Count of READM Measures Better.
Show data table
valuecountshare
0333261.5%
Not Available115021.2%
173713.6%
21613.0%
3280.5%
4100.2%
530.1%

Count of READM Measures No Different categorical feature

This column counts how many readmission (READM) measures at a hospital scored 'No Different' than the national rate, encoded as integers 1-9+ alongside a 'Not Available' sentinel. With 13 unique values and entropy ratio 0.92, the distribution is fairly flat across counts 1-9 (each ~370-500 rows), but 'Not Available' is the single largest bucket at 21.2% (1,150 of 5,421). That missingness-as-string is the main surprise and would corrupt any numeric aggregation if not handled.

Treatment: Cast to integer with 'Not Available' converted to NaN before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[100]:

saturn.columns["Count of READM Measures No Different"].stats

statvalue
n5,421
nulls0 (0.0%)
unique13
top_value Not Available
top_rate 0.2121
cardinality 13
entropy 3.408
entropy_ratio 0.9211
Fig 37.
Top values for Count of READM Measures No Different.
Show data table
valuecountshare
Not Available115021.2%
74979.2%
84919.1%
64808.9%
24287.9%
34287.9%
54267.9%
94187.7%
43987.3%
13726.9%
102494.6%
11811.5%
030.1%

Count of READM Measures Worse categorical feature

This appears to be a hospital-level count of readmission measures performing worse than the national rate, stored as a categorical/string field with values 0-7 plus a 'Not Available' sentinel. The distribution is heavily concentrated at '0' (55.1% of 5421 rows) with another 1150 rows marked 'Not Available', leaving genuine non-zero counts as a long tail that thins to just 1-2 hospitals at values 5, 6, and 7. The mixing of numeric strings with 'Not Available' is the main gotcha.

Treatment: Replace 'Not Available' with NaN and cast remaining values to integer before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[103]:

saturn.columns["Count of READM Measures Worse"].stats

statvalue
n5,421
nulls0 (0.0%)
unique9
top_value 0
top_rate 0.5512
cardinality 9
entropy 1.758
entropy_ratio 0.5545
Fig 38.
Top values for Count of READM Measures Worse.
Show data table
valuecountshare
0298855.1%
Not Available115021.2%
183915.5%
23085.7%
31051.9%
4260.5%
620.0%
520.0%
710.0%

READM Group Footnote numeric metadata

Likely a footnote/flag code attached to a hospital readmission group metric, encoded as a small integer rather than a true numeric quantity. Only 3 distinct values appear (min 5, max 22, median 19) and 78.79% of rows are null, so the column is sparse and categorical in nature. The non-null distribution is concentrated at the higher codes, with q1=5 and q3=19 indicating a bimodal split between two code clusters.

Treatment: Cast to categorical footnote code and treat nulls as 'no footnote' rather than imputing numerically.

anthropic:claude-opus-4-7 · confidence high
Out[106]:

saturn.columns["READM Group Footnote"].stats

statvalue
n5,421
nulls4,271 (78.8%)
unique3
min 5
max 22
mean 15.15
median 19
std 6.366
q1 5
q3 19
iqr 14
skew -0.9528
kurtosis -1.051
n_outliers 0
outlier_rate 0
zero_rate 0
alert: null_rate78.8% null
Fig 39.
Distribution of READM Group Footnote. Vertical dash marks the median.
Show data table
bincount
5 – 5.515323
5.515 – 6.030
6.03 – 6.5450
6.545 – 7.0610
7.061 – 7.5760
7.576 – 8.0910
8.091 – 8.6060
8.606 – 9.1210
9.121 – 9.6360
9.636 – 10.150
10.15 – 10.670
10.67 – 11.180
11.18 – 11.70
11.7 – 12.210
12.21 – 12.730
12.73 – 13.240
13.24 – 13.760
13.76 – 14.270
14.27 – 14.790
14.79 – 15.30
15.3 – 15.820
15.82 – 16.330
16.33 – 16.850
16.85 – 17.360
17.36 – 17.880
17.88 – 18.390
18.39 – 18.910
18.91 – 19.42795
19.42 – 19.940
19.94 – 20.450
20.45 – 20.970
20.97 – 21.480
21.48 – 2232

Pt Exp Group Measure Count categorical metadata

A binary categorical with only two values: the string "8" covering 84.08% of 5,421 rows and "Not Available" for the remaining 863. This looks like a measure-count field that is fixed at 8 when reported, otherwise marked as missing via a sentinel rather than a true null (null_rate is 0.0). Entropy ratio of 0.63 reflects that imbalance.

Treatment: Convert "Not Available" to a true null and treat as a binary missingness indicator; the column carries little signal otherwise.

anthropic:claude-opus-4-7 · confidence high
Out[109]:

saturn.columns["Pt Exp Group Measure Count"].stats

statvalue
n5,421
nulls0 (0.0%)
unique2
top_value 8
top_rate 0.8408
cardinality 2
entropy 0.6324
entropy_ratio 0.6324
Fig 40.
Top values for Pt Exp Group Measure Count.
Show data table
valuecountshare
8455884.1%
Not Available86315.9%

Count of Facility Pt Exp Measures categorical feature

This column is a binary categorical indicator with only two distinct values across all 5,421 rows: the literal string "8" (58.2%) and "Not Available" (41.8%). Despite being labeled as a count, it never varies numerically — every reporting facility either has exactly 8 measures or none reported, making this effectively a presence/absence flag with high entropy ratio (0.98). The 41.8% "Not Available" rate is a substantial missingness signal masquerading as a category.

Treatment: Recode as a binary available/not-available flag rather than treating as a numeric count.

anthropic:claude-opus-4-7 · confidence high
Out[112]:

saturn.columns["Count of Facility Pt Exp Measures"].stats

statvalue
n5,421
nulls0 (0.0%)
unique2
top_value 8
top_rate 0.5818
cardinality 2
entropy 0.9806
entropy_ratio 0.9806
Fig 41.
Top values for Count of Facility Pt Exp Measures.
Show data table
valuecountshare
8315458.2%
Not Available226741.8%

Pt Exp Group Footnote numeric metadata

This appears to be a footnote code attached to a 'Pt Exp Group' (patient experience group) measure, stored as a numeric but functioning as a categorical flag. Only 3 distinct values appear (min 5, median 5, max 22) and 58.18% of rows are null, indicating footnotes are applied sparingly to a minority of records. The bimodal-looking spread (Q1=5, Q3=19, kurtosis -1.66) confirms this is a small set of discrete codes rather than a true numeric measurement.

Treatment: Cast to categorical footnote code and treat nulls as 'no footnote' rather than missing.

anthropic:claude-opus-4-7 · confidence high
Out[115]:

saturn.columns["Pt Exp Group Footnote"].stats

statvalue
n5,421
nulls3,154 (58.2%)
unique3
min 5
max 22
mean 10.15
median 5
std 6.806
q1 5
q3 19
iqr 14
skew 0.571
kurtosis -1.658
n_outliers 0
outlier_rate 0
zero_rate 0
alert: null_rate58.2% null
Fig 42.
Distribution of Pt Exp Group Footnote. Vertical dash marks the median.
Show data table
bincount
5 – 5.4251440
5.425 – 5.850
5.85 – 6.2750
6.275 – 6.70
6.7 – 7.1250
7.125 – 7.550
7.55 – 7.9750
7.975 – 8.40
8.4 – 8.8250
8.825 – 9.250
9.25 – 9.6750
9.675 – 10.10
10.1 – 10.520
10.52 – 10.950
10.95 – 11.380
11.38 – 11.80
11.8 – 12.220
12.22 – 12.650
12.65 – 13.070
13.07 – 13.50
13.5 – 13.920
13.92 – 14.350
14.35 – 14.780
14.78 – 15.20
15.2 – 15.620
15.62 – 16.050
16.05 – 16.480
16.48 – 16.90
16.9 – 17.320
17.32 – 17.750
17.75 – 18.170
18.17 – 18.60
18.6 – 19.02795
19.02 – 19.450
19.45 – 19.880
19.88 – 20.30
20.3 – 20.730
20.73 – 21.150
21.15 – 21.570
21.57 – 2232

TE Group Measure Count categorical feature

Binary categorical column with only two values: '12' (84.1% of rows) and 'Not Available' (the remaining 863 rows). The literal '12' suggests this captures a count of measures per TE group, but it is stored as a string and effectively constant when present. The 'Not Available' sentinel functions as the only real source of variation.

Treatment: Convert to a boolean is_available flag; drop the constant '12' value.

anthropic:claude-opus-4-7 · confidence high
Out[118]:

saturn.columns["TE Group Measure Count"].stats

statvalue
n5,421
nulls0 (0.0%)
unique2
top_value 12
top_rate 0.8408
cardinality 2
entropy 0.6324
entropy_ratio 0.6324
Fig 43.
Top values for TE Group Measure Count.
Show data table
valuecountshare
12455884.1%
Not Available86315.9%

Count of Facility TE Measures categorical feature

This column reports the count of facility TE (timely & effective care) measures available per record, but it's stored as strings mixing numeric values ("4" through "12") with the sentinel "Not Available". The most common value is "Not Available" at 17.1% (928 of 5421), making missingness the modal category despite a reported null_rate of 0. Entropy ratio of 0.93 across 13 categories shows the non-null counts are spread fairly evenly, with "10" and "11" the dominant numeric values.

Treatment: Recode "Not Available" to null and cast remaining values to integer before modelling.

anthropic:claude-opus-4-7 · confidence high
Out[121]:

saturn.columns["Count of Facility TE Measures"].stats

statvalue
n5,421
nulls0 (0.0%)
unique13
top_value Not Available
top_rate 0.1712
cardinality 13
entropy 3.458
entropy_ratio 0.9343
Fig 44.
Top values for Count of Facility TE Measures.
Show data table
valuecountshare
Not Available92817.1%
1075914.0%
1172413.4%
954310.0%
83917.2%
53516.5%
123476.4%
63376.2%
72845.2%
42725.0%
32695.0%
21633.0%
1531.0%

TE Group Footnote numeric metadata

This appears to be a footnote reference code for a 'TE Group', stored numerically but functioning as a categorical pointer with only 3 distinct values across 5421 rows. It is overwhelmingly empty (82.88% null) and heavily concentrated at 19 (both q1 and q3 equal 19, iqr=0), producing a strong left skew (-2.43) and 133 outliers (14.33%) at the low end down to 5. The numeric stats like mean=17.58 are misleading given the column is effectively a small code set.

Treatment: Cast to categorical and treat nulls as 'no footnote'; do not use as a numeric feature.

anthropic:claude-opus-4-7 · confidence high
Out[124]:

saturn.columns["TE Group Footnote"].stats

statvalue
n5,421
nulls4,493 (82.9%)
unique3
min 5
max 22
mean 17.58
median 19
std 4.432
q1 19
q3 19
iqr 0
skew -2.43
kurtosis 4.12
n_outliers 133
outlier_rate 0.1433
zero_rate 0
alert: null_rate82.9% null
alert: high_skewskew=-2.43
alert: outliers14.3% rows beyond 1.5 IQR
Fig 45.
Distribution of TE Group Footnote. Vertical dash marks the median.
Show data table
bincount
5 – 5.567101
5.567 – 6.1330
6.133 – 6.70
6.7 – 7.2670
7.267 – 7.8330
7.833 – 8.40
8.4 – 8.9670
8.967 – 9.5330
9.533 – 10.10
10.1 – 10.670
10.67 – 11.230
11.23 – 11.80
11.8 – 12.370
12.37 – 12.930
12.93 – 13.50
13.5 – 14.070
14.07 – 14.630
14.63 – 15.20
15.2 – 15.770
15.77 – 16.330
16.33 – 16.90
16.9 – 17.470
17.47 – 18.030
18.03 – 18.60
18.6 – 19.17795
19.17 – 19.730
19.73 – 20.30
20.3 – 20.870
20.87 – 21.430
21.43 – 2232

How to cite

click to copy

BibTeX
@misc{saturn-healthcare-cms-hospitals-2025-2026,
  author       = {Steuber, Luke},
  title        = {Saturn reading: healthcare cms hospitals 2025},
  year         ={2026},
  howpublished = {\url{https://dr.eamer.dev/saturn/view/healthcare-cms_hospitals_2025}},
  note         = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:claude-opus-4-7},
}
APA
Steuber, L. (2026). Saturn reading: healthcare cms hospitals 2025. Source: /home/coolhand/datasets/us-inequality-atlas/healthcare/cms_hospitals_2025.csv. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:claude-opus-4-7). Retrieved from https://dr.eamer.dev/saturn/view/healthcare-cms_hospitals_2025