Reads as: riskier than 62.4% of the 14,684 facilities in the snf peer group. percentile within peer group, 100 = highest risk. Grade bands are fixed percentile cuts (F is the top 5% of peer risk), so a grade is a position, not an absolute level.
weighted_contribution sums to pre_rank_index over rows where counts_toward_index is true. The composite is the facility's percentile position of that index within its peer group, so contributions explain the input, and the rank explains the score.
ML signals — parallel engine
8
Kind
Finding
Signal
Subject
First seen
connection
Owner fleet risk far above national
+22.4 vs natl
SANDERSON CLARK
58 facilities
connection
Owner fleet risk far above national
+21.5 vs natl
FANNIN COUNTY HOSPITAL AUTHORITY
54 facilities
connection
Owner spans multiple chains
18 chains
ENSIGN SERVICES INC
286 facilities
connection
Owner spans multiple chains
17 chains
BURNAM SOON
335 facilities
connection
Owner spans multiple chains
17 chains
KEETCH CHAD
283 facilities
connection
Owner spans multiple chains
12 chains
THE ENSIGN GROUP INC
123 facilities
connection
Owner spans multiple chains
11 chains
STANDARD BEARER HEALTHCARE OP LP
83 facilities
connection
Buyer assembling a chain (5+ takeovers/24mo)
8 facilities
FANNIN COUNTY HOSPITAL AUTHORITY
8 facilities
Findings from the always-on scanning layer: anomalies on this facility, connections through its current owners and past buyers. Runs beside the deterministic composite, never inside it. Full board on the ML Lab page.
Change-of-ownership footprint in the CMS Provider of Services file: control-family, legal-name and address deltas across quarterly snapshots, plus certification reset recency and Medicare tenure.
R23/W4-3. Deterministic logistic p(Medicare termination within 12m), SNF only. Label = first POS termination date (any code: voluntary closure, involuntary termination, merger exit); facilities already terminated by the panel date are excluded, not counted as safe. Trained on panels 2024-07/2024-10/2025-01 (n=46,466, 283 positives), evaluated on the held-out later panel 2025-04 BEFORE shipping: AUC 0.971, top-decile lift 9.5x, top-decile capture 95.4% of the 65 terminations that followed. Separability is high because closures announce themselves in the data: collapsing occupancy is the strongest signal, and the learned NEGATIVE weight on 12m deficiency counts is the surveys-stop signature of a facility winding down, not a claim that clean inspections are dangerous. Same 15 as-of-date features and anti-leakage chassis as p_chow_12m; SFF entry rejected as a label (only one month of SFF history exists, so as-of transitions cannot be reconstructed). Score = probability x 100; grade NULL. Not in any composite.
R22/W4-2. Deterministic logistic p(CHOW within 12m), SNF only. Trained on panels 2024-07/2024-10/2025-01 (n=50,700, 1,207 positives), evaluated on the held-out later panel 2025-04 BEFORE shipping: AUC 0.874, top-decile lift 5.0x (top 10% of predictions captured 49.6% of the CHOWs that actually closed in the next 12 months). Shipped coefficients are the evaluated ones; no post-holdout refit. Caveat: holdout positives (133) run below the training base rate because recent CHOWs surface in public records with a lag, so measured lift is conservative. Features are as-of-date public records: PBJ staffing level/trend/contract share (quarterly history to 2022Q1), deficiency and CMP counts (12m), ownership tenure and churn from CHOW-evidenced transactions, beds, occupancy, ownership type, chain size. Chain membership and ownership type are current-state (history not published). SFF and star ratings deliberately excluded (no as-of history). Notable learned direction: long ownership tenure RAISES sale odds and a recent prior CHOW lowers them. Score = probability x 100; grade is NULL because a probability is not a quality letter. Not in any composite.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later regulatory_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later regulatory_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later staffing_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later staffing_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Rows with counts_toward_composite false come from models that are addressable or retracted rather than default. They exist and may be informative, but they did not enter the published composite and must not be summed as though they had.
p_adverse_action_12m: probability the facility's Medicare participation terminates within 12 months (any POS termination code; already-terminated facilities are excluded, not scored safe). Deterministic logistic over as-of-date public records, SNF only. Holdout (2025-04 panel, evaluated before shipping): AUC 0.971, top-decile lift 9.5x. Closures announce themselves: collapsing occupancy dominates, and fewer recent surveys is a winding-down signature. inputs.features holds raw feature values, inputs.contributions each feature's standardized pull on the log-odds. Predictions never enter the composite. See /v1/models. | p_chow_12m: probability of a change of ownership within 12 months. Deterministic logistic over as-of-date public records, SNF only. Holdout (2025-04 panel, evaluated before shipping): AUC 0.874, top-decile lift 5.0x. inputs.features holds raw feature values, inputs.contributions each feature's standardized pull on the log-odds. Predictions never enter the composite. See /v1/models for full notes.
Probability the facility's Medicare participation ends within 12 months, from public records only. Red bars raise exit odds. A negative pull from deficiencies is the winding-down signature — surveys stop as a facility empties — not evidence that clean inspections are dangerous.
Staffing vs peers
16
2025Q4 HPRD
This facility
TX median
National median
National p25–p75
Total nurse
2.79
2.67
3.28
2.90–3.77
RN
0.26
0.24
0.39
0.25–0.58
Weekend total
2.44
2.56
3.11
—
Weekday total
2.93
2.72
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
65.6
2.79
0.26
0.59
1.94
2.44
1.2%
2025Q3
92
61.1
2.75
0.21
0.67
1.87
2.40
1.6%
2025Q2
91
59.6
2.88
0.14
0.74
2.01
2.53
1.8%
2025Q1
90
64.0
2.66
0.12
0.71
1.83
2.41
1.1%
2024Q4
92
63.7
2.67
0.11
0.73
1.83
2.31
2.5%
2024Q3
92
66.9
2.53
0.18
0.63
1.73
2.27
2.4%
2024Q2
91
63.9
2.49
0.16
0.67
1.67
2.23
4.6%
2024Q1
91
64.8
2.50
0.17
0.70
1.63
2.25
9.5%
2023Q4
92
62.0
2.71
0.21
0.59
1.91
2.59
4.6%
2023Q3
92
61.0
3.15
0.10
0.78
2.27
2.85
4.7%
2023Q2
91
61.6
3.10
0.06
0.82
2.22
2.82
5.4%
2023Q1
90
65.1
2.97
0.07
0.78
2.12
2.73
4.3%
2022Q4
92
69.7
2.81
0.06
0.76
2.00
2.60
6.9%
2022Q3
92
63.1
3.49
0.05
1.07
2.37
3.31
17.4%
2022Q2
91
63.3
3.10
0.06
0.85
2.20
2.98
11.3%
2022Q1
90
62.9
3.40
0.06
1.02
2.32
3.30
19.1%
HPRD is census-weighted: total hours over the quarter divided by total resident-days, not an average of daily ratios. Source is CMS Payroll-Based Journal daily records; only SNFs report PBJ, so other settings legitimately return zero rows.
Penalties
0
No penalties on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Deficiencies
10
D × 8E × 2
deficiencies by survey year
Survey
Type
Tag
Deficiency
Scope
Corrected
2026-03-19
Health · complaint
F0880
Provide and implement an infection prevention and control program.
D
2026-04-23
2025-02-06
Health
F0689
Ensure that a nursing home area is free from accident hazards and provides adequate supervision to prevent accidents.
D
2025-03-06
2025-02-06
Health
F0759
Ensure medication error rates are not 5 percent or greater.
D
2025-03-06
2025-02-06
Health
F0761
Ensure drugs and biologicals used in the facility are labeled in accordance with currently accepted professional principles; and all drugs and biologicals must be stored in locked compartments, separately locked, compartments for controlled drugs.
D
2025-03-06
2025-02-06
Health
F0842
Safeguard resident-identifiable information and/or maintain medical records on each resident that are in accordance with accepted professional standards.
D
2025-03-06
2024-01-19
Health · complaint
F0690
Provide appropriate care for residents who are continent or incontinent of bowel/bladder, appropriate catheter care, and appropriate care to prevent urinary tract infections.
D
2024-02-06
2024-01-19
Health · complaint
F0814
Dispose of garbage and refuse properly.
D
2024-02-06
2022-11-17
Health
F0644
Coordinate assessments with the pre-admission screening and resident review program; and referring for services as needed.
D
2022-12-10
2022-11-17
Health
F0812
Procure food from sources approved or considered satisfactory and store, prepare, distribute and serve food in accordance with professional standards.
E
2022-12-10
2022-11-17
Health
F0842
Safeguard resident-identifiable information and/or maintain medical records on each resident that are in accordance with accepted professional standards.
E
2022-12-10
scope_severity uses the CMS letter grid: A is least serious, L most. J, K and L are immediate jeopardy. Rows are the surveyor's findings of record, not the model's opinion.
Licensure actions
0
No licensure actions on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Ownership
24
Owner
Role
Pct
From
Status
Source
FANNIN COUNTY HOSPITAL AUTHORITY
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2026-05-01
current
pecos_ownership
ANDERSON, SANDY
OPERATIONAL/MANAGERIAL CONTROL
—
2026-05-01
current
pecos_ownership
BURNAM, SOON
OPERATIONAL/MANAGERIAL CONTROL
—
2026-05-01
current
pecos_ownership
COLORADO COUNTY DEVELOPMENT GROUP, LLC
—
—
2024-01-01
current
tx_hhsc_directory
ENSIGN SERVICES INC
ADP OF THE SNF
—
2026-02-13
current
pecos_ownership
FANNIN COUNTY HOSPITAL AUTHORITY
—
—
2024-01-01
current
tx_hhsc_directory
KEETCH, CHAD
CORPORATE OFFICER
—
2011-03-01
current
pecos_ownership
KLAUS, BART
MANAGING CONTROL - GOVERNING BODY
—
2026-05-01
current
pecos_ownership
MONTEZUMA STREET HEALTH HOLDINGS LLC
ADP OF THE SNF
—
2026-05-01
current
pecos_ownership
ROLLING PRAIRIE HEALTHCARE LLC
ADP OF THE SNF
—
2026-04-16
current
pecos_ownership
ROLLING PRAIRIE HEALTHCARE LLC
OPERATIONAL/MANAGERIAL CONTROL
—
2026-05-01
current
pecos_ownership
SANDERSON, CLARK
CORPORATE OFFICER
—
2026-05-01
current
pecos_ownership
STANDARD BEARER HEALTHCARE OP, LP
ADP OF THE SNF
—
2026-05-01
current
pecos_ownership
THE ENSIGN GROUP INC
ADP OF THE SNF
—
2026-05-01
current
pecos_ownership
COLORADO COUNTY DEVELOPMENT GROUP LLC
5% OR GREATER MORTGAGE INTEREST
100%
2024-01-01
ended 2026-05-18
pecos_ownership
COLORADO COUNTY DEVELOPMENT GROUP LLC
OPERATIONAL/MANAGERIAL CONTROL
100%
2014-01-01
ended 2026-05-18
pecos_ownership
FANNIN COUNTY HOSPITAL AUTHORITY
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2024-01-01
ended 2026-05-18
pecos_ownership
JAMES STEIN
5% OR GREATER MORTGAGE INTEREST
25%
2014-01-01
ended 2026-05-18
pecos_ownership
PAUL STEIN
5% OR GREATER MORTGAGE INTEREST
25%
2014-01-01
ended 2026-05-18
pecos_ownership
ROBERT RYE
5% OR GREATER MORTGAGE INTEREST
25%
2014-01-01
ended 2026-05-18
pecos_ownership
ROBERT V RYE LIV TR DTD 10042022
5% OR GREATER MORTGAGE INTEREST
25%
2024-01-01
ended 2026-05-18
pecos_ownership
CLARK SANDERSON
CORPORATE OFFICER
0%
2017-01-01
ended 2026-05-18
pecos_ownership
BART KLAUS
OPERATIONAL/MANAGERIAL CONTROL
—
2014-01-01
ended 2026-05-18
pecos_ownership
SANDY ANDERSON
ADP OF THE SNF
—
2014-01-01
ended 2026-05-18
pecos_ownership
PECOS ownership and managing-control associations. Current edges have no end date in the source; historical edges are retained.
Related-party costs
0
No related-party cost years on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Cost-report related-party spend by fiscal year. has_propco flags real-estate counterparties.
Most recent same-state, same-setting trades. Most CHOW-derived trades carry no disclosed consideration, so price, $/bed, and cap rate show only where a sale price was resolved from a deed or filing — blanks are honest, not missing data.
Market rent context
30
Geo
Kind
BR
Amount
As of
Source
county 48089
acs median gross
0
$231
2024-12-31
CENSUS_ACS5
county 48089
fmr
0
$892
2025-10-01
HUD_USER_FMR
county 48089
acs median gross
1
$273
2024-12-31
CENSUS_ACS5
county 48089
fmr
1
$917
2025-10-01
HUD_USER_FMR
county 48089
acs median gross
2
$930
2024-12-31
CENSUS_ACS5
county 48089
fmr
2
$1,147
2025-10-01
HUD_USER_FMR
county 48089
acs median gross
3
$1,261
2024-12-31
CENSUS_ACS5
county 48089
fmr
3
$1,375
2025-10-01
HUD_USER_FMR
county 48089
fmr
4
$1,688
2025-10-01
HUD_USER_FMR
county 48089
acs median gross
$926
2024-12-31
CENSUS_ACS5
county 48089
acs recent mover gross
$936
2024-12-31
CENSUS_ACS5
zcta 78934
acs median gross
2
$904
2024-12-31
CENSUS_ACS5
zcta 78934
acs median gross
3
$1,188
2024-12-31
CENSUS_ACS5
zcta 78934
acs median gross
$869
2024-12-31
CENSUS_ACS5
zcta 78934
acs recent mover gross
$886
2024-12-31
CENSUS_ACS5
zip 78934
payment standard 110
0
$979
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 90
0
$801
2025-10-01
HUD_USER_SAFMR
zip 78934
safmr
0
$890
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 110
1
$1,001
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 90
1
$819
2025-10-01
HUD_USER_SAFMR
zip 78934
safmr
1
$910
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 110
2
$1,254
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 90
2
$1,026
2025-10-01
HUD_USER_SAFMR
zip 78934
safmr
2
$1,140
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 110
3
$1,507
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 90
3
$1,233
2025-10-01
HUD_USER_SAFMR
zip 78934
safmr
3
$1,370
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 110
4
$1,848
2025-10-01
HUD_USER_SAFMR
zip 78934
payment standard 90
4
$1,512
2025-10-01
HUD_USER_SAFMR
zip 78934
safmr
4
$1,680
2025-10-01
HUD_USER_SAFMR
ACS median gross rents and HUD FMR/SAFMR for the facility's county and ZIP. Context for underwriting, not facility pricing.