Reads as: riskier than 70.8% 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
15
Kind
Finding
Signal
Subject
First seen
connection
Owner fleet risk far above national
+27.3 vs natl
INTERNATIONAL BANK OF COMMERCE
7 facilities
connection
Owner spans multiple chains
18 chains
PLANTE MORAN PLLC
55 facilities
connection
Owner spans multiple chains
15 chains
AEGIS THERAPIES INC
32 facilities
connection
Owner spans multiple chains
9 chains
FELLBAUM ERNEST
26 facilities
connection
Owner spans multiple chains
9 chains
TRIDENT HEALTHCARE SERVICES INC
24 facilities
connection
Owner spans multiple chains
9 chains
STUDER STANLEY
26 facilities
connection
Owner spans multiple chains
8 chains
NUTRITIOUS LIFESTYLES INC
18 facilities
connection
Owner spans multiple chains
8 chains
TOUCHSTONE COMMUNITIES INC
23 facilities
connection
Owner spans multiple chains
8 chains
ZUROVEC DARRELL
23 facilities
connection
Owner spans multiple chains
8 chains
SEHLKE BRYON
22 facilities
connection
Owner spans multiple chains
8 chains
CASTILLO LYNNEA
23 facilities
connection
Owner spans multiple chains
8 chains
CARVAJAL PHARMACY LTC
22 facilities
connection
Owner fleet enforcement cluster
43% fined
INTERNATIONAL BANK OF COMMERCE
7 facilities
connection
Owner fleet enforcement cluster
41% fined
SEHLKE BRYON
22 facilities
connection
Owner fleet enforcement cluster
41% fined
STUDER STANLEY
27 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
15
2025Q4 HPRD
This facility
TX median
National median
National p25–p75
Total nurse
2.37
2.67
3.28
2.90–3.77
RN
0.39
0.24
0.39
0.25–0.58
Weekend total
2.28
2.56
3.11
—
Weekday total
2.40
2.72
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
99.4
2.37
0.39
0.59
1.38
2.28
2.0%
2025Q3
92
94.9
2.36
0.43
0.48
1.45
2.33
2.2%
2025Q2
91
94.4
2.44
0.49
0.46
1.50
2.34
1.9%
2024Q4
92
61.4
3.39
0.64
0.63
2.11
3.38
3.3%
2024Q3
92
82.3
3.29
0.40
0.82
2.07
3.16
0.5%
2024Q2
91
82.1
2.83
0.30
0.68
1.86
2.52
0.0%
2024Q1
91
84.2
2.40
0.30
0.65
1.44
2.13
0.0%
2023Q4
92
84.8
2.36
0.28
0.64
1.45
2.20
0.0%
2023Q3
92
83.5
2.36
0.17
0.70
1.50
2.30
0.0%
2023Q2
91
78.5
2.56
0.09
0.76
1.71
2.52
0.0%
2023Q1
90
73.5
2.32
0.09
0.72
1.51
2.34
0.0%
2022Q4
92
71.3
2.51
0.08
0.77
1.66
2.54
0.0%
2022Q3
92
74.7
2.75
0.10
0.82
1.83
2.65
0.0%
2022Q2
91
72.0
2.88
0.22
0.88
1.78
2.65
0.0%
2022Q1
90
75.9
2.57
0.24
0.75
1.58
2.45
0.0%
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.
Coordinate assessments with the pre-admission screening and resident review program; and referring for services as needed.
E
2025-06-28
2025-05-29
Health
F0657
Develop the complete care plan within 7 days of the comprehensive assessment; and prepared, reviewed, and revised by a team of health professionals.
D
2025-06-28
2025-05-29
Health · complaint
F0760
Ensure that residents are free from significant medication errors.
E
2025-06-28
2025-05-29
Health
F0812
Procure food from sources approved or considered satisfactory and store, prepare, distribute and serve food in accordance with professional standards.
E
2025-06-28
2025-04-19
Health · complaint
F0609
Timely report suspected abuse, neglect, or theft and report the results of the investigation to proper authorities.
D
2025-04-20
2024-11-21
Health · complaint
F0689
Ensure that a nursing home area is free from accident hazards and provides adequate supervision to prevent accidents.
J
2024-11-20
2024-09-01
Health · complaint
F0838
Conduct and document a facility-wide assessment to determine what resources are necessary to care for residents competently during both day-to-day operations (including nights and weekends) and emergencies.
F
2024-09-24
2024-09-01
Health · complaint
F0842
Safeguard resident-identifiable information and/or maintain medical records on each resident that are in accordance with accepted professional standards.
E
2024-09-24
2024-03-14
Health · complaint
F0679
Provide activities to meet all resident's needs.
E
2024-04-12
2024-03-14
Health
F0732
Post nurse staffing information every day.
C
2024-03-22
2024-03-14
Health
F0880
Provide and implement an infection prevention and control program.
D
2024-04-11
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
39
Owner
Role
Pct
From
Status
Source
MAVERICK COUNTY HOSPITAL DISTRICT
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2024-09-17
current
pecos_ownership
AEGIS THERAPIES, INC.
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
BENAVIDES, LUIS
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
BONILLA, NESTOR
CORPORATE OFFICER
—
2007-01-01
current
pecos_ownership
CARVAJAL PHARMACY LTC
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
CASTILLO, LYNNEA
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-03-09
current
pecos_ownership
CHERIE VON DOHLEN BY PASS TRUST
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
CHVD 2020 LIFETIME FAMILY TRUST
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
CTVD HOLDINGS LTD
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
FELLBAUM, ERNEST
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
GONZALES, RICARDO
ADP OF THE SNF
—
2024-08-12
current
pecos_ownership
INTERNATIONAL BANK OF COMMERCE
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
LAREDO OPERATOR 3, LTD
ADP OF THE SNF
—
2025-03-09
current
pecos_ownership
LAREDO OPERATOR 3, LTD
OPERATIONAL/MANAGERIAL CONTROL
—
2024-09-17
current
pecos_ownership
LAREDO OPERATOR 3, LTD
—
—
2024-09-17
current
tx_hhsc_directory
LAREDO REALTY 3, LTD.
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
MAURICIO, LUIS
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
MAVERICK COUNTY HOSPITAL DISTRICT
—
—
2024-09-17
current
tx_hhsc_directory
NUTRITIOUS LIFESTYLES, INC.
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
PLANTE & MORAN PLLC
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
SEHLKE, BRYON
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
STUDER, STANLEY
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
TDVD, LTD.
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
TGVD 2020 LIFETIME FAMILY TRUST
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
TOUCHSTONE COMMUNITIES INC
ADP OF THE SNF
—
2025-03-09
current
pecos_ownership
TOUCHSTONE LAREDO PROPERTIES LTD
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
TRIDENT HEALTH SERVICES INC
ADP OF THE SNF
—
2024-09-17
current
pecos_ownership
VON DOHLEN, CHRISTOPHER
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-05-29
current
pecos_ownership
VON DOHLEN, PATRICK
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-05-29
current
pecos_ownership
VON DOHLEN, TERESA
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-05-29
current
pecos_ownership
VON DOHLEN, TIMOTHY
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-05-29
current
pecos_ownership
ZUROVEC, DARRELL
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-03-09
current
pecos_ownership
NESTOR BONILLA
CORPORATE OFFICER
0%
2007-01-01
ended 2026-05-18
pecos_ownership
BRYON SEHLKE
ADP OF THE SNF
—
2024-09-17
ended 2026-05-18
pecos_ownership
ERNEST FELLBAUM
ADP OF THE SNF
—
2024-09-17
ended 2026-05-18
pecos_ownership
LUIS BENAVIDES
ADP OF THE SNF
—
2024-09-17
ended 2026-05-18
pecos_ownership
LUIS MAURICIO
ADP OF THE SNF
—
2024-09-17
ended 2026-05-18
pecos_ownership
RICARDO GONZALES
OPERATIONAL/MANAGERIAL CONTROL
—
2024-08-12
ended 2026-05-18
pecos_ownership
STANLEY STUDER
ADP OF THE SNF
—
2024-09-17
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
5
FY end
Total allowable
Rent
Home office
Therapy
Staffing
Counterparties
PropCo
2024-12-31
$189,340
—
—
—
$98,403
1
—
2023-12-31
$298,731
—
—
—
$166,201
1
—
2022-12-31
$350,437
—
—
—
—
1
—
2021-12-31
$398,145
—
$398,145
—
—
1
—
2020-12-31
$732,583
—
$732,583
—
—
1
—
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
36
Geo
Kind
BR
Amount
As of
Source
county 48479
acs median gross
0
$795
2024-12-31
CENSUS_ACS5
county 48479
fmr
0
$956
2025-10-01
HUD_USER_FMR
county 48479
acs median gross
1
$790
2024-12-31
CENSUS_ACS5
county 48479
fmr
1
$962
2025-10-01
HUD_USER_FMR
county 48479
acs median gross
2
$1,002
2024-12-31
CENSUS_ACS5
county 48479
fmr
2
$1,161
2025-10-01
HUD_USER_FMR
county 48479
acs median gross
3
$1,227
2024-12-31
CENSUS_ACS5
county 48479
fmr
3
$1,499
2025-10-01
HUD_USER_FMR
county 48479
acs median gross
4
$1,218
2024-12-31
CENSUS_ACS5
county 48479
fmr
4
$1,551
2025-10-01
HUD_USER_FMR
county 48479
acs median gross
5
$2,038
2024-12-31
CENSUS_ACS5
county 48479
acs median gross
$1,027
2024-12-31
CENSUS_ACS5
county 48479
acs recent mover gross
$1,063
2024-12-31
CENSUS_ACS5
zcta 78041
acs median gross
0
$917
2024-12-31
CENSUS_ACS5
zcta 78041
acs median gross
1
$795
2024-12-31
CENSUS_ACS5
zcta 78041
acs median gross
2
$987
2024-12-31
CENSUS_ACS5
zcta 78041
acs median gross
3
$1,214
2024-12-31
CENSUS_ACS5
zcta 78041
acs median gross
4
$1,216
2024-12-31
CENSUS_ACS5
zcta 78041
acs median gross
5
$1,929
2024-12-31
CENSUS_ACS5
zcta 78041
acs median gross
$978
2024-12-31
CENSUS_ACS5
zcta 78041
acs recent mover gross
$936
2024-12-31
CENSUS_ACS5
zip 78041
payment standard 110
0
$1,067
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 90
0
$873
2025-10-01
HUD_USER_SAFMR
zip 78041
safmr
0
$970
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 110
1
$1,078
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 90
1
$882
2025-10-01
HUD_USER_SAFMR
zip 78041
safmr
1
$980
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 110
2
$1,298
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 90
2
$1,062
2025-10-01
HUD_USER_SAFMR
zip 78041
safmr
2
$1,180
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 110
3
$1,672
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 90
3
$1,368
2025-10-01
HUD_USER_SAFMR
zip 78041
safmr
3
$1,520
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 110
4
$1,738
2025-10-01
HUD_USER_SAFMR
zip 78041
payment standard 90
4
$1,422
2025-10-01
HUD_USER_SAFMR
zip 78041
safmr
4
$1,580
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.