psgscoring

Open-source AASM-compliant respiratory scoring for polysomnography.

PyPI Python License Tests

Paper

Rombaut B, Rombaut B, Rombaut C, et al. Automated Polysomnography Scoring for Clinical Sleep Medicine: An Open-Source Platform Validated Against 59 Independent Scorer Sessions on PSG-IPA. Manuscript in preparation, 2026.

Technical details (signal processing chain, classification logic, all twelve bias corrections): Technical Reference (Online Supplement)

What this library does

psgscoring detects and classifies respiratory events (apneas, hypopneas, RERAs) in polysomnography recordings following AASM rules. It extends YASA (Vallat & Walker, eLife 2021) from sleep staging into a complete clinical respiratory scoring pipeline.

Three contributions that distinguish this library:

  1. Twelve bias corrections — the first systematic identification and empirical quantification of six over-counting and six under-counting mechanisms in automated respiratory scoring
  2. AHI confidence interval — every study is scored at three stringency levels (strict/standard/sensitive), yielding a per-study robustness grade (A/B/C) rather than a single AHI number
  3. Clinical auditability — every event carries a confidence score, classification rule index, and per-correction counters, enabling the reviewing physician to verify individual scoring decisions

Installation

pip install psgscoring

Requirements: Python ≥3.9, numpy, scipy, mne. No GPU required.

Quick Start

import mne
from psgscoring import run_pneumo_analysis

# Load EDF and provide a hypnogram (e.g., from YASA)
raw = mne.io.read_raw_edf("recording.edf", preload=True)
hypnogram = ["W", "N1", "N2", "N2", "N3", ...]  # per 30-s epoch

# Run the full pipeline
results = run_pneumo_analysis(raw, hypnogram, scoring_profile="aasm_v3_rec")

# Access results
resp = results["respiratory"]["summary"]
print(f"AHI: {resp['ahi_total']}, Severity: {resp['severity']}")
print(f"Events: {resp['n_obstructive']} OA, {resp['n_hypopnea']} Hyp")

# AHI confidence interval
interval = results["ahi_interval"]
print(f"AHI interval: [{interval['strict']['ahi']}–{interval['sensitive']['ahi']}]")
print(f"Robustness: {interval['robustness_grade']}")

Scoring Profiles

Parameter Strict Standard Sensitive
Hypopnea threshold ≥30% ≥30% ≥25%
SpO₂ nadir window 30 s 45 s 45 s
Peak-based detection No Yes Yes

list_profiles() enumerates the full registry (AASM v1/v2/v3, CMS/Medicare, Chicago 1999, and the NSRR dataset profile).

aasm_v3_breath — breath-graded hypopnea scoring (v0.13.0, opt-in)

run_pneumo_analysis(raw, hypnogram, scoring_profile="aasm_v3_breath")

A second hypopnea detector that takes the breath, not the sample, as the unit. The AASM speaks of peak signal excursions; this scores them directly. Five differences from the default detector:

  1. Breath-level events. An event is a run of consecutive breaths below the threshold, so boundaries land on breath transitions and a recovery breath ends the run by itself — no smoothing, and the merge/split problem that depresses event-F1 largely disappears.
  2. Two-pass patient calibration. Pass 1 finds the incontestable events; pass 2 measures the baseline from only the breathing that is not an event, and derives that patient's own SpO₂ delay by cross-correlation instead of assuming a fixed 30–45 s window.
  3. Graded AASM predicates. The rule structure stays literally the Rule 1A conjunction — ≥30% reduction AND ≥10 s AND (≥3% desaturation OR arousal) — but each threshold gets a tolerance rather than being infinitely sharp.
  4. Every event carries p_scored plus a criteria dict giving each predicate's contribution, so the audit trail says why, not just what.
  5. One strictness axis (hypopnea_strictness, default 0.50) instead of three parameter combinations.

Scope is hypopneas only; apneas keep the existing detector.

Status — opt-in, not the default. On PSG-IPA (5 recordings, 12 scorers) the median event-F1 rises 0.343 → 0.434, the percentile within the inter-scorer distribution p6 → p17, and mean |ΔAHI| against the scorer median falls 1.84 → 0.29. On MESA the paired advantage replicates on two disjoint held-out samples of 50 (p = 0.0069 and p = 0.0016). But the two datasets disagree on the absolute level by ~16 AHI points, and until that is explained the existing clinical output stays the default. See docs/interim_conclusie_klinisch_gebruik.md.

Validation

PSG-IPA (PhysioNet): 5 recordings, 59 independent scorer sessions. Mean |ΔAHI| = 1.8/h, Pearson r = 0.997, severity concordance 4/5 (standard profile). See the paper for full results.

MESA (NSRR, external cohort): q=7 high-quality holdout, n=92 (held out from the optional LightGBM re-classifier's training). LightGBM-augmented AHI: bias −0.02/h, MAE 5.3/h, Pearson r = 0.87 against the NSRR nsrr_ahi_hp3u reference. SHHS-1 validation in progress.

Twelve Bias Corrections

# Correction Direction Clinical impact
1 Post-apnea baseline inflation Over-counting Prevents false Mild→Moderate
2 SpO₂ cross-contamination Over-counting Flags uncertain coupling
3 Cheyne-Stokes trough scoring Over-counting Prevents HF misdiagnosis as OSA
4 Low-confidence defaults Over-counting Confidence stratification
5 Artefact-flank exclusion Over-counting Prevents post-disconnect events
6 Local baseline validation Over-counting Rejects inflated-baseline FPs
7 Peak-based amplitude detection Under-counting AASM-conformant breath-level
8 Extended SpO₂ nadir window Under-counting Catches delayed desaturations
9 Flow smoothing removal Under-counting Eliminated +54 FPs on PSG-IPA
10 Position signal auto-mapping Under-counting Handles raw ADC encoding
11 Configurable profiles Under-counting Sensitivity adjustment per study
12 Flattening-based RERA Under-counting Flow limitation without amplitude drop

Architecture

~8,900 lines across 17 submodules, 115 unit tests (CI: Python 3.9–3.12):

constants · utils · signal · breath · classify · spo2 · plm · ancillary · respiratory · pipeline · ml_classifier · profiles · postprocess · signal_quality · signal_quality_channels · ecg_effort · _types

Related

  • YASAFlaskified — web platform integrating psgscoring with YASA staging, multilingual PDF reports, EDF+ export, and FHIR R4
  • YASA — AI-based sleep staging (Vallat & Walker, eLife 2021)
  • slaapkliniek.be — live instance (no installation required)

Citation

@article{rombaut2026psgscoring,
  title     = {Automated Polysomnography Scoring for Clinical Sleep Medicine:
               An Open-Source Platform Validated Against 59 Independent
               Scorer Sessions on {PSG-IPA}},
  author    = {Rombaut, Bart and Rombaut, Briek and Rombaut, Cedric},
  year      = {2026},
  note      = {Manuscript in preparation}
}

Disclaimer

psgscoring is research software — not a medical device. It is not CE-marked (MDR 2017/745) or FDA-cleared. All outputs are research-grade estimates that must be reviewed by a qualified clinician before any diagnostic or therapeutic decision. See DISCLAIMER.md for the full text.

License

BSD-3-Clause. See LICENSE.

Contact: bart.rombaut@gmail.com

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.32.0)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for bartromb from gravatar.com bartromb

Credits

Author/Maintainer: Briek Rombaut, Cedric Rombaut

License expression

BSD-3-Clause
View SPDX License List

Requires

Python >=3.9

Provides Extra

full ml test plot

Tags

polysomnography PSG sleep AASM apnea hypopnea AHI respiratory scoring sleep-staging YASA hypoxic-burden

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

psgscoring-0.13.0.tar.gz (1.3 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

psgscoring-0.13.0-py3-none-any.whl (1.3 MB view details)

Uploaded Python 3

File details

Details for the file psgscoring-0.13.0.tar.gz.

File metadata

  • Download URL: psgscoring-0.13.0.tar.gz
  • Upload date:
  • Size: 1.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for psgscoring-0.13.0.tar.gz
Algorithm Hash digest
SHA256 a7a2c8caccd5f12408cbdcafb4a67c597219ad104f144da861b859801c8420e9
MD5 1a138d341cbdc684ec0db17eb9f51ad8
BLAKE2b-256 ac511507cd2a29df3e4d9f4e00e4180833cb05eae356afa1de8b9a956dbf4d51

See more details on using hashes here.

File details

Details for the file psgscoring-0.13.0-py3-none-any.whl.

File metadata

  • Download URL: psgscoring-0.13.0-py3-none-any.whl
  • Upload date:
  • Size: 1.3 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for psgscoring-0.13.0-py3-none-any.whl
Algorithm Hash digest
SHA256 787513bbadae992bf5c2a50d792a494f1851001ea8d4c6e9c89a86a396399024
MD5 9dde57460e58aa18b9feb1e2810c8a4b
BLAKE2b-256 f07b9ca81396a7272770b8794fc76805d76e43a35169cfea3b4da6d29af2afc8

See more details on using hashes here.

Release history Release notifications | RSS feed

0.32.0

2 files

0.31.6

2 files

0.31.5

2 files

0.31.4

2 files

0.31.3

2 files

0.31.2

2 files

0.31.1

2 files

0.31.0

2 files

0.30.0

2 files

0.29.0

2 files

0.28.1

2 files

0.28.0

2 files

0.27.7

2 files

0.27.6

2 files

0.27.5

2 files

0.27.4

2 files

0.27.3

2 files

0.27.0

2 files

0.26.0

2 files

0.25.0

2 files

0.24.0

2 files

0.23.0

2 files

0.22.0

2 files

0.21.0

2 files

0.20.0

2 files

0.19.1

2 files

0.19.0

2 files

0.18.0

2 files

0.17.0

2 files

0.15.2

2 files

0.15.1

2 files

0.15.0

2 files

0.14.9

2 files

0.14.8

2 files

0.14.7

2 files

0.14.6

2 files

0.14.5

2 files

0.14.4

2 files

0.14.3

2 files

0.14.2

2 files

0.14.1

2 files

0.14.0

2 files

0.13.2

2 files

0.13.1

2 files

This release

0.13.0 This release

2 files

0.12.2

2 files

0.12.1

2 files

0.12.0

2 files

0.11.0

2 files

0.10.0

2 files

0.9.0

2 files

0.7.6

2 files

0.7.3

2 files

0.7.2

2 files

0.7.1

2 files

0.7.0

2 files

0.6.2

2 files

0.6.1

2 files

0.6.0

2 files

0.5.2

2 files

0.5.1

2 files

0.5.0

2 files

0.4.5

2 files

0.4.4

2 files

0.4.3

2 files

0.4.2

2 files

0.3.2

2 files

0.3.1

2 files

0.2.963

2 files

0.2.962

2 files

0.2.961

2 files

0.2.951

2 files

0.2.96

2 files

0.2.95

2 files

0.2.94

2 files

0.2.93

2 files

0.2.92

2 files

0.2.91

2 files

0.2.9

2 files

0.2.8

2 files

0.2.7

2 files

0.2.6

2 files

0.2.4

2 files

0.2.3

2 files

0.2.2

2 files

0.2.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page