Sleep & CPAP Report — 2026-09-14

🚩 Flags

• Leak seal broke down tonight — the largest single-night leak spike of the past two weeks. Leak_90 = 4.8 L/min (7d avg 1.37, +250%; 30d avg 2.08, +131%) — the highest Leak_90 since 2026-09-03 (7.2). Leak_Max = 27.6 (7d avg 16.6, +66%; 30d avg 17.6, +57%) — tied roughly with the two prior peaks in this dataset (09-03 and 09-04, both 28.8). Leak_Avg = 0.86 (7d avg 0.66, +30%). This ends a 6-night run of well-controlled leak (Leak_90 ≤ 1.2 every night from 09-08 through 09-13) and reverses the clean leak trend that had been noted repeatedly in prior reports. Sleep architecture was still good tonight, so this is CPAP-side isolated — but if it repeats tomorrow, that's a mask-fit signal worth tracking.
• AHI 2.55 — second consecutive night of elevated AHI (yesterday 2.60). Two-night mean 2.575 vs 7d avg 2.08 (+24%). Still well under the clinical threshold of 5, but this makes 3 of the last 4 nights running above the 30d baseline of 1.98.
• RERA count 2 — biggest departure from baseline of any metric tonight. 7d avg 0.43 → tonight's 2 = +367%. RERA has been 0 on 5 of the past 7 nights. Combined with 12 OAs and 2 CAs, tonight's respiratory event profile is broader-based (more event types firing) than any recent night.
• CA 2 — highest in a month other than 09-10's outlier of 3. 7d avg 1.0. Notable in the context of the leak spike (mask instability can transiently elevate CA counts via airflow disruption).
• Sleep architecture actually held up well despite the leak/event increase. Deep% 14.93% (+29% vs 7d avg 11.54%) — a real rebound from 09-13's collapse to 8.29%. Awake time just 3.0 min (7d avg 10.25, -71%) — lowest in at least 10 nights. Sleep efficiency 99.13%. The CPAP-side deterioration did NOT translate into a fragmented night — which is consistent with the historical pattern that leak has only a weak negative association with deep sleep (r = -0.185 across 75 nights) rather than a strong one.
• Sleep was shorter than baseline. TIB 345.7 min (5h 45.7m), Total Sleep 342.7 min (5h 42.7m). -8.1% vs 7d TIB, -9.9% vs 30d TIB. The shortest full night of the recent 10-night window. Usage hours 5.88 (-7.3% vs 7d) — matches the shorter time in bed rather than early mask removal.
• Pressure_90 = 10.26 — machine pushed to near its recent-high. Same value as 09-05 and 09-13 (all recent-window peaks). Consistent with the machine responding to elevated obstructive/leak load.

Two-day pattern to watch: 09-13 was flagged as a sudden architectural collapse in the absence of a leak issue (physiological driver suspected). 09-14 is the mirror image — CPAP-side stress (leak, AHI, RERA) with intact sleep architecture. If the leak spike repeats tomorrow, mask-fit is the leading suspect and worth a physical inspection of cushion, headgear tension, and pillow position.

Summary Table — Night of 2026-09-14

Metric	Value
Sleep start	2026-09-14 23:51:00-05:00
Time in bed	345.7 min (5h 45.7m)
Total sleep	342.7 min (5h 42.7m)
Sleep efficiency	99.13%
Awake time	3.0 min
Core (N1+N2) sleep	217.3 min / 63.40%
Deep (N3) sleep	51.2 min / 14.93%
REM	74.3 min / 21.67%
CPAP usage hours	5.88
Session count	1
AHI	2.55
RDI	2.89
Obstructive apneas (OA)	12
Hypopneas (H)	1
Central apneas (CA)	2
Unclassified apneas (UA)	0
RERA	2
Pressure_Avg	7.43
Pressure_Min	4.00
Pressure_Max	11.14
Pressure_90th	10.26
Leak_Avg	0.86
Leak_Max	27.6
Leak_90th	4.8
FL_Avg	0.0147
FL_P95	0.10
FL_Max	0.49
Min_Above_005	34.1
Min_Above_010	15.8
Min_Above_020	4.1
Frac_NonZero (FL samples)	20.41%

Comparison to Trailing Averages

Metric	Tonight	7d avg	30d avg	Δ vs 7d	Δ vs 30d
AHI	2.55	2.08	1.98	+22.8%	+28.8%
OA count	12.00	10.00	9.57	+20.0%	+25.4%
H count	1.00	2.14	2.57	-53.3%	-61.0%
CA count	2.00	1.00	0.80	+100.0%	+150.0%
RERA count	2.00	0.43	0.80	+366.7%	+150.0%
Pressure_Avg	7.43	7.28	7.49	+2.1%	-0.8%
Pressure_90	10.26	9.88	10.05	+3.8%	+2.1%
Leak_Avg	0.86	0.66	0.79	+29.7%	+9.1%
Leak_Max	27.60	16.63	17.60	+66.0%	+56.8%
Leak_90th	4.80	1.37	2.08	+250.0%	+130.8%
Usage hours	5.88	6.35	6.51	-7.3%	-9.6%
FL_P95	0.10	0.089	0.099	+12.9%	+0.7%
Min_Above_010	15.80	15.31	18.33	+3.2%	-13.8%
Min_Above_020	4.10	3.71	4.18	+10.4%	-1.8%
Awake min	3.01	10.25	9.27	-70.6%	-67.5%
TIB min	345.73	376.04	383.78	-8.1%	-9.9%
Total sleep min	342.72	365.79	374.51	-6.3%	-8.5%
Deep %	14.93	11.54	13.62	+29.4%	+9.6%
REM %	21.67	23.04	23.76	-6.0%	-8.8%
Core %	63.40	65.42	62.62	-3.1%	+1.2%

Week-over-Week Deltas (recent 7d 09/08–09/14 vs prior 7d 09/01–09/07)

Metric	Recent 7d	Prior 7d	Δ	Δ %
AHI	2.177	2.033	+0.144	+7.1%
OA	10.429	9.571	+0.857	+9.0%
CA	1.143	0.429	+0.714	+166.7%
Pressure_Avg	7.307	7.400	-0.093	-1.3%
Leak_Avg	0.613	0.906	-0.293	-32.3%
Leak_90	1.543	2.571	-1.029	-40.0%
Deep %	12.520	14.608	-2.088	-14.3%
REM %	22.930	23.126	-0.196	-0.8%
Awake min	8.817	10.322	-1.505	-14.6%
Sleep min	359.559	372.681	-13.122	-3.5%
FL_P95	0.087	0.096	-0.009	-9.0%
Min_Above_010	14.529	16.729	-2.200	-13.2%

Recent-week Leak averages still tracking BELOW the prior week — tonight's spike is an isolated event within an otherwise-declining weekly trend. Deep% recent-week is down 14.3% (weighed by 09-05, 09-07, 09-08, 09-13's low-deep nights); REM stable; CA count up notably week-over-week.

Recent 10-Night Context

Date	AHI	OA	CA	PAvg	P90	LAvg	LMax	L90	FL_P95	MinAbv010	MinAbv020	Deep%	REM%	Awake
2026-09-05	2.66	11	1	7.59	10.26	0.79	19.2	2.4	0.11	19.8	7.4	5.35	25.35	13.55
2026-09-06	1.40	7	1	6.72	9.44	0.27	14.4	0.0	0.08	14.4	3.8	17.64	19.40	10.04
2026-09-07	1.85	9	1	7.23	10.40	1.21	21.6	3.6	0.11	21.3	2.2	8.05	22.47	13.05
2026-09-08	2.25	9	0	7.38	9.34	1.12	18.0	3.6	0.09	15.0	3.7	7.85	19.22	11.04
2026-09-09	1.40	7	1	7.68	10.52	0.63	13.2	1.2	0.11	20.5	4.8	15.10	29.01	2.51
2026-09-10	2.10	10	3	7.14	9.30	0.14	7.2	0.0	0.07	9.7	1.4	11.44	20.34	7.02
2026-09-11	2.53	13	0	6.57	9.52	0.62	24.0	0.0	0.05	8.9	2.4	11.97	21.87	10.54
2026-09-12	1.81	8	1	7.17	9.92	0.45	14.4	1.2	0.08	12.7	3.9	18.06	27.63	9.53
2026-09-13	2.60	14	1	7.78	10.16	0.47	18.0	0.0	0.11	19.1	7.6	8.29	20.78	18.06
2026-09-14	2.55	12	2	7.43	10.26	0.86	27.6	4.8	0.10	15.8	4.1	14.93	21.67	3.01

CPAP → Sleep-Stage Correlations (all 75 matched nights)

Correlations computed across full available history (2026-06-23 → 2026-09-14).

Pair	the user r	Interpretation
AHI vs deep_pct	+0.030	negligible
AHI vs awake_min	+0.061	negligible
OA vs awake_min	+0.092	negligible
CA vs deep_pct	+0.031	negligible
Leak_Avg vs deep_pct	-0.182	weak negative — higher leak, slightly less deep sleep
Leak_90 vs deep_pct	-0.185	weak negative — same direction
Leak_Max vs awake_min	+0.079	negligible
FL_P95 vs awake_min	-0.093	negligible
Min_Above_010 vs deep_pct	+0.011	negligible

Bucket comparison (Leak_90 median split, median = 2.4): - Low-leak nights (n=49): mean deep% 15.83, awake 15.05 min - High-leak nights (n=26): mean deep% 13.33, awake 12.72 min - Δ (high – low): deep% -2.50 pp, awake -2.33 min

Tonight breaks the leak → deep pattern in the opposite direction from 09-13: despite Leak_90 of 4.8 (a clearly high-leak night), Deep% was 14.93 (near the median for high-leak nights). Awake time was 3.0 min — the lowest in the recent window. The leak spike tonight did not fragment sleep. That's a benign single-night data point; what makes it worth flagging is not sleep quality but the sudden mask-seal deterioration itself, which is a CPAP-hardware signal worth tracking to see if it repeats.

Caveats

• Sleep session started at 23:51:00 on 2026-09-14 — matched to the 2026-09-14 CPAP file (same-calendar-date convention).
• Apple Watch SpO2/pulse channels not present in current CPAP CSV export.
• Correlations are directional/small-effect only — single-night deviations often exceed what correlations alone would predict.
• All flagged metrics remain within clinically safe ranges (AHI < 5); the flags mark deviations from the user's own recent baseline, not clinical thresholds.
• The health-report-2026-07-18-to-2026-07-19 2.json duplicate file was again ignored in favor of the primary copy.
• Matched-night count is 75 (up from 74 in prior report) — one additional match after re-processing.