Reads as: riskier than 35.7% 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
19
Kind
Finding
Signal
Subject
First seen
connection
Owner fleet risk far above national
+26.2 vs natl
THREADGILL SHARLYN
10 facilities
connection
Owner fleet risk far above national
+26.2 vs natl
THREADGILL MORGAN
10 facilities
connection
Owner fleet risk far above national
+26.2 vs natl
THREADGILL FORREST
10 facilities
connection
Owner fleet risk far above national
+23.7 vs natl
THOMPSON JOHNNY
74 facilities
connection
Owner fleet risk far above national
+22.5 vs natl
MARTEL MICHAEL
8 facilities
connection
Owner spans multiple chains
6 chains
SMITHERS JEFFREY
10 facilities
connection
Owner spans multiple chains
5 chains
THREADGILL SHARLYN
10 facilities
connection
Owner spans multiple chains
5 chains
THREADGILL MORGAN
10 facilities
connection
Owner spans multiple chains
5 chains
THREADGILL FORREST
10 facilities
connection
Owner spans multiple chains
4 chains
MARTEL MICHAEL
8 facilities
connection
Owner fleet enforcement cluster
70% fined
THREADGILL SHARLYN
10 facilities
connection
Owner fleet enforcement cluster
70% fined
THREADGILL FORREST
10 facilities
connection
Owner fleet enforcement cluster
70% fined
THREADGILL MORGAN
10 facilities
connection
Owner fleet enforcement cluster
63% fined
MARTEL MICHAEL
8 facilities
connection
Owner fleet enforcement cluster
50% fined
THE SMITHERS MANAGEMENT TRUST
6 facilities
connection
Owner fleet enforcement cluster
45% fined
THOMPSON JOHNNY
74 facilities
connection
Owner fleet enforcement cluster
40% fined
COMPTON CHARLES
5 facilities
connection
Owner fleet enforcement cluster
40% fined
COMPTON JAMES
5 facilities
connection
Owner fleet enforcement cluster
40% fined
COMPTON KRIS
5 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 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
2.97
2.67
3.28
2.90–3.77
RN
0.25
0.24
0.39
0.25–0.58
Weekend total
2.65
2.56
3.11
—
Weekday total
3.10
2.72
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
93.8
2.97
0.25
0.82
1.91
2.65
0.0%
2025Q3
92
92.8
2.98
0.20
0.79
2.00
2.62
0.0%
2025Q2
91
95.5
3.11
0.10
0.93
2.09
2.73
0.0%
2025Q1
90
101.4
3.02
0.19
0.86
1.97
2.62
0.0%
2024Q4
92
101.5
3.17
0.17
0.87
2.14
2.68
0.0%
2024Q3
92
100.0
3.15
0.13
0.80
2.22
2.95
0.0%
2024Q2
91
92.2
2.95
0.11
0.89
1.95
2.78
0.0%
2024Q1
91
97.8
2.91
0.17
0.81
1.93
2.74
0.0%
2023Q4
92
95.2
3.07
0.13
0.96
1.99
2.75
0.0%
2023Q3
92
91.6
3.00
0.12
0.89
1.98
2.88
0.0%
2023Q2
91
93.0
3.07
0.13
0.95
2.00
2.81
0.0%
2023Q1
90
91.4
3.05
0.15
1.02
1.88
2.79
0.0%
2022Q4
92
81.2
3.12
0.07
1.16
1.89
2.97
0.0%
2022Q3
92
64.9
3.61
0.09
1.37
2.16
3.42
0.1%
2022Q2
91
56.8
3.25
0.08
1.03
2.15
3.12
0.0%
2022Q1
90
57.6
3.16
0.03
1.02
2.12
3.04
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.
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
5
D × 5
deficiencies by survey year
Survey
Type
Tag
Deficiency
Scope
Corrected
2025-07-09
Health
F0641
Ensure each resident receives an accurate assessment.
D
2025-07-24
2025-07-09
Health
F0656
Develop and implement a complete care plan that meets all the resident's needs, with timetables and actions that can be measured.
D
2025-07-24
2025-07-09
Health
F0755
Provide pharmaceutical services to meet the needs of each resident and employ or obtain the services of a licensed pharmacist.
D
2025-07-24
2025-07-09
Health
F0880
Provide and implement an infection prevention and control program.
D
2025-07-24
2024-05-31
Health
F0656
Develop and implement a complete care plan that meets all the resident's needs, with timetables and actions that can be measured.
D
2024-06-09
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
25
Owner
Role
Pct
From
Status
Source
AV REHAB LLC
OPERATIONAL/MANAGERIAL CONTROL
—
2022-05-01
current
pecos_ownership
AV REHAB, LLC
—
—
2025-05-01
current
tx_hhsc_directory
BROAD RIVER HEALTHCARE, LLC
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
BROGDON, JACK
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
COMPTON, CHARLES
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
COMPTON, JAMES
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
COMPTON, KRIS
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
MARTEL FINANCIAL INVESTMENTS, LLC
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
MARTEL, MICHAEL
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
RBC HARLINGEN GROUP INVESTMENTS, LLC
ADP OF THE SNF
—
2022-05-01
current
pecos_ownership
SMITHERS, JEFFREY
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-03-28
current
pecos_ownership
THE SMITHERS MANAGEMENT TRUST
5% OR GREATER MORTGAGE INTEREST
—
2022-05-01
current
pecos_ownership
THOMPSON, JOHNNY
CORPORATE OFFICER
—
2024-07-01
current
pecos_ownership
THREADGILL, FORREST
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-03-28
current
pecos_ownership
THREADGILL, MORGAN
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-03-28
current
pecos_ownership
THREADGILL, SHARLYN
OPERATIONAL/MANAGERIAL CONTROL
—
2022-05-01
current
pecos_ownership
WEST WHARTON COUNTY HOSPITAL DISTRICT
—
—
2025-05-01
current
tx_hhsc_directory
WEST WHARTON COUNTY HOSPITAL DISTRICT
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2022-05-01
ended 2026-05-18
pecos_ownership
MICHAEL MARTEL
5% OR GREATER MORTGAGE INTEREST
33%
2022-05-01
ended 2026-05-18
pecos_ownership
CHARLES COMPTON
5% OR GREATER MORTGAGE INTEREST
8%
2022-05-01
ended 2026-05-18
pecos_ownership
JAMES COMPTON
5% OR GREATER MORTGAGE INTEREST
8%
2022-05-01
ended 2026-05-18
pecos_ownership
KRIS COMPTON
5% OR GREATER MORTGAGE INTEREST
8%
2022-05-01
ended 2026-05-18
pecos_ownership
JOHNNY THOMPSON
CORPORATE OFFICER
0%
2024-07-01
ended 2026-05-18
pecos_ownership
JACK BROGDON
ADP OF THE SNF
—
2022-05-01
ended 2026-05-18
pecos_ownership
SHARLYN THREADGILL
OPERATIONAL/MANAGERIAL CONTROL
—
2022-05-01
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
3
FY end
Total allowable
Rent
Home office
Therapy
Staffing
Counterparties
PropCo
2022-04-30
$81,600
—
—
—
—
1
—
2021-12-31
$239,602
—
—
—
—
1
—
2020-12-31
$21,726
—
—
—
—
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
35
Geo
Kind
BR
Amount
As of
Source
county 48061
acs median gross
0
$724
2024-12-31
CENSUS_ACS5
county 48061
fmr
0
$773
2025-10-01
HUD_USER_FMR
county 48061
acs median gross
1
$729
2024-12-31
CENSUS_ACS5
county 48061
fmr
1
$866
2025-10-01
HUD_USER_FMR
county 48061
acs median gross
2
$893
2024-12-31
CENSUS_ACS5
county 48061
fmr
2
$1,047
2025-10-01
HUD_USER_FMR
county 48061
acs median gross
3
$1,112
2024-12-31
CENSUS_ACS5
county 48061
fmr
3
$1,414
2025-10-01
HUD_USER_FMR
county 48061
acs median gross
4
$1,170
2024-12-31
CENSUS_ACS5
county 48061
fmr
4
$1,479
2025-10-01
HUD_USER_FMR
county 48061
acs median gross
5
$1,575
2024-12-31
CENSUS_ACS5
county 48061
acs median gross
$912
2024-12-31
CENSUS_ACS5
county 48061
acs recent mover gross
$1,019
2024-12-31
CENSUS_ACS5
zcta 78550
acs median gross
0
$843
2024-12-31
CENSUS_ACS5
zcta 78550
acs median gross
1
$768
2024-12-31
CENSUS_ACS5
zcta 78550
acs median gross
2
$947
2024-12-31
CENSUS_ACS5
zcta 78550
acs median gross
3
$1,114
2024-12-31
CENSUS_ACS5
zcta 78550
acs median gross
4
$1,072
2024-12-31
CENSUS_ACS5
zcta 78550
acs median gross
$900
2024-12-31
CENSUS_ACS5
zcta 78550
acs recent mover gross
$1,020
2024-12-31
CENSUS_ACS5
zip 78550
payment standard 110
0
$869
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 90
0
$711
2025-10-01
HUD_USER_SAFMR
zip 78550
safmr
0
$790
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 110
1
$968
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 90
1
$792
2025-10-01
HUD_USER_SAFMR
zip 78550
safmr
1
$880
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 110
2
$1,177
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 90
2
$963
2025-10-01
HUD_USER_SAFMR
zip 78550
safmr
2
$1,070
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 110
3
$1,584
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 90
3
$1,296
2025-10-01
HUD_USER_SAFMR
zip 78550
safmr
3
$1,440
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 110
4
$1,661
2025-10-01
HUD_USER_SAFMR
zip 78550
payment standard 90
4
$1,359
2025-10-01
HUD_USER_SAFMR
zip 78550
safmr
4
$1,510
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.