Reads as: riskier than 78.1% 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
20
Kind
Finding
Signal
Subject
First seen
connection
Owner fleet risk far above national
+27.0 vs natl
TRILOGY HEALTHCARE MASTER TENANT IX LLC
6 facilities
connection
Owner spans multiple chains
14 chains
DAVIS DAVID
122 facilities
connection
Owner spans multiple chains
14 chains
BARNEY LEIGH
122 facilities
connection
Owner spans multiple chains
14 chains
PARAGON OUTPATIENT REHABILITATION SERVICES LLC
58 facilities
connection
Owner spans multiple chains
13 chains
TRILOGY REAL ESTATE INVESTMENT TRUST
68 facilities
connection
Owner spans multiple chains
13 chains
AMERICAN HEALTHCARE REIT INC
68 facilities
connection
Owner spans multiple chains
13 chains
TRILOGY MANAGEMENT SERVICES LLC
119 facilities
connection
Owner spans multiple chains
13 chains
TRILOGY INVESTORS LLC
67 facilities
connection
Owner spans multiple chains
13 chains
GAHC3 TRILOGY JV LLC
69 facilities
connection
Owner spans multiple chains
13 chains
TRILOGY REIT HOLDINGS LLC
68 facilities
connection
Owner spans multiple chains
13 chains
AMERICAN HEALTHCARE REIT HOLDINGS LP
67 facilities
connection
Owner spans multiple chains
12 chains
KEYBANK NATIONAL ASSOCIATION
43 facilities
connection
Owner spans multiple chains
12 chains
GAHC4 TRILOGY JV LLC
68 facilities
connection
Owner spans multiple chains
11 chains
TRILOGY HEALTHCARE HOLDINGS INC
31 facilities
connection
Owner spans multiple chains
11 chains
TRILOGY PROPERTY HOLDINGS LLC
42 facilities
connection
Owner spans multiple chains
10 chains
TRILOGY PROPCO FINANCE LLC
22 facilities
connection
Owner spans multiple chains
10 chains
TRILOGY HEALTH SERVICES LLC
30 facilities
connection
Owner spans multiple chains
9 chains
TRILOGY OPCO LLC
24 facilities
connection
Owner spans multiple chains
8 chains
TRILOGY PRO SERVICES LLC
23 facilities
connection
Owner spans multiple chains
6 chains
PARACHA IBRAR
11 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
IN median
National median
National p25–p75
Total nurse
2.78
2.85
3.28
2.90–3.77
RN
0.59
0.40
0.39
0.25–0.58
Weekend total
2.46
2.71
3.11
—
Weekday total
2.90
2.90
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
46.2
2.78
0.59
0.80
1.39
2.46
0.0%
2025Q3
92
44.1
3.05
0.66
0.76
1.63
2.78
0.0%
2025Q2
91
45.0
2.87
0.66
0.69
1.52
2.64
0.0%
2025Q1
90
45.1
3.12
0.66
0.71
1.76
2.87
0.0%
2024Q4
92
45.4
2.88
0.56
0.66
1.66
2.64
0.0%
2024Q3
92
47.4
2.72
0.52
0.72
1.49
2.52
0.0%
2024Q2
91
46.4
2.60
0.54
0.72
1.34
2.44
0.0%
2024Q1
91
45.4
2.95
0.50
0.71
1.75
2.71
0.0%
2023Q4
92
46.1
2.88
0.52
0.67
1.68
2.83
0.0%
2023Q3
92
44.3
3.11
0.41
0.70
2.00
2.96
0.0%
2023Q2
91
45.6
3.37
0.33
0.87
2.17
3.18
0.0%
2023Q1
90
46.2
2.92
0.43
0.76
1.74
2.91
0.0%
2022Q4
92
45.5
2.52
0.37
0.70
1.45
2.50
0.0%
2022Q3
92
43.5
2.58
0.32
0.76
1.50
2.41
0.0%
2022Q2
91
48.2
2.38
0.36
0.68
1.34
2.15
0.0%
2022Q1
90
45.1
2.61
0.43
0.82
1.36
2.56
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
1
D × 1
Survey
Type
Tag
Deficiency
Scope
Corrected
2023-09-26
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
2023-09-27
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
43
Owner
Role
Pct
From
Status
Source
HARRISON COUNTY HOSPITAL
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2022-03-01
current
pecos_ownership
AMERICAN HEALTHCARE REIT HOLDINGS LP
ADP OF THE SNF
—
2021-10-01
current
pecos_ownership
AMERICAN HEALTHCARE REIT INC
ADP OF THE SNF
—
2018-10-01
current
pecos_ownership
BARNEY, LEIGH
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-06-24
current
pecos_ownership
BODNEY, STEPHEN
MANAGING CONTROL - GOVERNING BODY
—
2022-01-01
current
pecos_ownership
BROWN, RICHARD
TRUSTEE OF THE SNF
—
1991-06-15
current
pecos_ownership
CLUNIE, LISA
MANAGING CONTROL - GOVERNING BODY
—
2022-01-08
current
pecos_ownership
DAVIS, DAVID
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-06-24
current
pecos_ownership
GAHC3 TRILOGY JV LLC
ADP OF THE SNF
—
2015-12-01
current
pecos_ownership
GAHC4 TRILOGY JV LLC
ADP OF THE SNF
—
2018-10-01
current
pecos_ownership
HESS, JUDY
TRUSTEE OF THE SNF
—
2016-01-01
current
pecos_ownership
KEYBANK NATIONAL ASSOCIATION
5% OR GREATER MORTGAGE INTEREST
—
2023-05-01
current
pecos_ownership
PADGETT, NATALIE
OPERATIONAL/MANAGERIAL CONTROL
—
2022-10-30
current
pecos_ownership
PARACHA, IBRAR
ADP OF THE SNF
—
2024-06-01
current
pecos_ownership
PARAGON OUTPATIENT REHABILITATION SERVICES LLC
ADP OF THE SNF
—
2015-12-01
current
pecos_ownership
RHS PARTNERS LLC
ADP OF THE SNF
—
2025-06-24
current
pecos_ownership
RHS PARTNERS OF MOORESVILLE, LLC
OPERATIONAL/MANAGERIAL CONTROL
—
2019-03-01
current
pecos_ownership
RHS PROPCO MOORESVILLE LLC
ADP OF THE SNF
—
2019-06-28
current
pecos_ownership
SHICKLES, LARRY
TRUSTEE OF THE SNF
—
2022-02-01
current
pecos_ownership
SHIREMAN, KATHY
TRUSTEE OF THE SNF
—
2014-05-01
current
pecos_ownership
TRILOGY HEALTH SERVICES LLC
ADP OF THE SNF
—
2019-06-28
current
pecos_ownership
TRILOGY HEALTHCARE HOLDINGS INC
ADP OF THE SNF
—
2025-06-24
current
pecos_ownership
TRILOGY HEALTHCARE MASTER TENANT IX LLC
ADP OF THE SNF
—
2025-06-24
current
pecos_ownership
TRILOGY INVESTORS LLC
ADP OF THE SNF
—
2015-12-01
current
pecos_ownership
TRILOGY MANAGEMENT SERVICES LLC
ADP OF THE SNF
—
2015-12-01
current
pecos_ownership
TRILOGY OPCO LLC
ADP OF THE SNF
—
2025-06-24
current
pecos_ownership
TRILOGY PRO SERVICES LLC
ADP OF THE SNF
—
2025-06-24
current
pecos_ownership
TRILOGY PROPCO FINANCE LLC
ADP OF THE SNF
—
2019-06-28
current
pecos_ownership
TRILOGY PROPERTY HOLDINGS LLC
ADP OF THE SNF
—
2019-06-28
current
pecos_ownership
TRILOGY REAL ESTATE INVESTMENT TRUST
ADP OF THE SNF
—
2015-12-01
current
pecos_ownership
TRILOGY REIT HOLDINGS LLC
ADP OF THE SNF
—
2015-12-01
current
pecos_ownership
WHITIS, HARRIS
TRUSTEE OF THE SNF
—
2021-01-01
current
pecos_ownership
WISEMAN, MARK
TRUSTEE OF THE SNF
—
2021-09-01
current
pecos_ownership
HARRIS WHITIS
TRUSTEE OF THE SNF
—
2021-01-01
ended 2026-05-18
pecos_ownership
IBRAR PARACHA
OPERATIONAL/MANAGERIAL CONTROL
—
2024-06-01
ended 2026-05-18
pecos_ownership
JUDY HESS
TRUSTEE OF THE SNF
—
2016-01-01
ended 2026-05-18
pecos_ownership
KATHY SHIREMAN
TRUSTEE OF THE SNF
—
2014-05-01
ended 2026-05-18
pecos_ownership
LARRY SHICKLES
TRUSTEE OF THE SNF
—
2022-02-01
ended 2026-05-18
pecos_ownership
LISA CLUNIE
MANAGING CONTROL - GOVERNING BODY
—
2022-01-08
ended 2026-05-18
pecos_ownership
MARK WISEMAN
MANAGING CONTROL - GOVERNING BODY
—
2021-09-01
ended 2026-05-18
pecos_ownership
NATALIE PADGETT
ADP OF THE SNF
—
2022-10-30
ended 2026-05-18
pecos_ownership
RICHARD BROWN
MANAGING CONTROL - GOVERNING BODY
—
1991-06-15
ended 2026-05-18
pecos_ownership
STEPHEN BODNEY
TRUSTEE OF THE SNF
—
2022-01-01
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
5
FY end
Total allowable
Rent
Home office
Therapy
Staffing
Counterparties
PropCo
2024-12-31
$1,820,688
—
—
$618,874
$225,430
4
—
2023-12-31
$1,744,333
—
—
$607,069
$211,174
4
—
2022-12-31
$1,579,293
—
—
$618,477
$145,112
4
—
2021-12-31
$1,597,797
—
—
$535,550
$158,219
3
—
2020-12-31
$1,196,820
—
—
$618,580
$101,302
3
—
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
31
Geo
Kind
BR
Amount
As of
Source
county 18109
fmr
0
$1,118
2025-10-01
HUD_USER_FMR
county 18109
acs median gross
1
$757
2024-12-31
CENSUS_ACS5
county 18109
fmr
1
$1,267
2025-10-01
HUD_USER_FMR
county 18109
acs median gross
2
$983
2024-12-31
CENSUS_ACS5
county 18109
fmr
2
$1,473
2025-10-01
HUD_USER_FMR
county 18109
acs median gross
3
$1,304
2024-12-31
CENSUS_ACS5
county 18109
fmr
3
$1,907
2025-10-01
HUD_USER_FMR
county 18109
acs median gross
4
$1,604
2024-12-31
CENSUS_ACS5
county 18109
fmr
4
$2,338
2025-10-01
HUD_USER_FMR
county 18109
acs median gross
$1,042
2024-12-31
CENSUS_ACS5
county 18109
acs recent mover gross
$1,160
2024-12-31
CENSUS_ACS5
zcta 46158
acs median gross
1
$794
2024-12-31
CENSUS_ACS5
zcta 46158
acs median gross
2
$990
2024-12-31
CENSUS_ACS5
zcta 46158
acs median gross
3
$1,255
2024-12-31
CENSUS_ACS5
zcta 46158
acs median gross
4
$1,696
2024-12-31
CENSUS_ACS5
zcta 46158
acs median gross
$1,084
2024-12-31
CENSUS_ACS5
zip 46158
payment standard 110
0
$1,144
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 90
0
$936
2025-10-01
HUD_USER_SAFMR
zip 46158
safmr
0
$1,040
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 110
1
$1,298
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 90
1
$1,062
2025-10-01
HUD_USER_SAFMR
zip 46158
safmr
1
$1,180
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 110
2
$1,507
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 90
2
$1,233
2025-10-01
HUD_USER_SAFMR
zip 46158
safmr
2
$1,370
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 110
3
$1,947
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 90
3
$1,593
2025-10-01
HUD_USER_SAFMR
zip 46158
safmr
3
$1,770
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 110
4
$2,387
2025-10-01
HUD_USER_SAFMR
zip 46158
payment standard 90
4
$1,953
2025-10-01
HUD_USER_SAFMR
zip 46158
safmr
4
$2,170
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.