MiniMed 640G cuts hypoglycemia; mother delivers a 4,137 g boy

MiniMed 640G predictive low-glucose suspend cut hypoglycemia in a T1D woman after two miscarriages; term birth of a 4,137 g boy.

AI system

System

Medtronic MiniMed sensor-augmented pump / automated insulin delivery with predictive low glucose suspend (SmartGuard)

Model

Not assessed

Release

Exact release not established.

Application developer

Medtronic

Role

The pump predicted low glucose and suspended insulin delivery.

Configuration

The initial event involved a MiniMed 640G. A later report involved a MiniMed 780G.

Inputs and outputs

Not assessed

Autonomy

Not assessed

Workflow

A person with type 1 diabetes and frequent or unrecognized hypoglycemia uses a Medtronic pump with CGM and predictive low glucose suspend enabled. Sensor glucose is predicted to fall and the algorithm suspends basal insulin. Hypoglycemia frequency and variability fall and the clinical goal (pregnancy, restored awareness) is reached.

Human oversight

Not assessed

Relation to AI

The pump's predictive algorithm autonomously suspended insulin for about four hours a day. The authors link this to fewer hypoglycemic episodes and lower variability. Obstetric and diabetes care were delivered by clinicians. The causal link to carrying the pregnancy is inferred, not demonstrated.

AI contribution

The pump's predictive algorithm autonomously suspended insulin for about four hours a day. The authors link this to fewer hypoglycemic episodes and lower variability. Obstetric and diabetes care were delivered by clinicians. The causal link to carrying the pregnancy is inferred, not demonstrated.

Benefits

Outcome identifiers

Not assessed

Benefit

hypoglycemic episodes fell from 2.1–2.5 to 1.4 per day

Category

Improved Physical Health

Status

Not assessed

Beneficiary groups

People.

Beneficiaries

Not assessed

Reach

Not assessed

Distribution and access

Not assessed

Duration

Not assessed

Expected?

Yes

Costs and harms

Not assessed

Measurement

Studies

Not assessed

Study design

Not assessed

Measurement

Not assessed

Setting and sample

Not assessed

Measures

hypoglycemic episodes fell from 2.1–2.5 to 1.4 per day

Comparison

her two earlier pregnancies on a MiniMed 620G sensor-augmented pump without predictive low glucose suspend

Results

Reference: Hypoglycemic episodes (/day) 2.5 and 2.1; time with AUC below 70 mg/dL 1.1% and 1.4%. Result: Hypoglycemic episodes (/day) 1.4; mean AUC < 70 mg/dL of 0.5%.

Additional value from AI

Not assessed

Limitations

Not assessed

Denominators

Not assessed

Materials for replication

Not assessed

Money

Kind of value

Not assessed

Amount

Not assessed

Currency and prices

Not assessed

Period and unit

Not assessed

Realization

Not assessed

Recipients and payers

Not assessed

Gross or net

Not assessed

Included costs

Not assessed

Comparison

Not assessed

Method

Not assessed

Return and payback

Not assessed

People and places

Participants

Developer: Medtronic.

Jurisdictions

Developer: Ireland.

Ownership and control

Not assessed

Dependencies

Not assessed

Cross-border connections

Not assessed

Geopolitical implications

Not assessed

Follow-up

Conditions for replication

Sensor is worn and calibrated with suspend enabled. The user does not override suspensions. Clinical follow-up adjusts settings.

Replication attempts

1 follow-up entries. Benefit recurred: 1.

Later findings

No development for this patient after the 2021 case report was found; the 2025 MiniMed 780G report concerns a different patient.

Availability

Not assessed

Institutional decision

Not assessed

Grounds

Not assessed

Action and result

Not assessed

Success criterion

Not assessed

Evidence

Source numbers

AIBD-0028-source-0001–0003

Citations

Numbered references below.

Language

Not assessed

Source relationships

Operator

Original evidence

Not assessed

Access and versions

Not assessed

Supported findings

Not assessed

Evidence strength

Not assessed

Missing evidence

Not assessed

Grades

Assessed benefits

People.

Depth

People: 3.

Reasons

People: After two miscarriages, hypoglycemia frequency and glucose variability fell on the device and the pregnancy reached term with a healthy infant. A life-changing benefit, though the source does not prove the device caused the live birth.

Observed or intended

Not assessed

Rubric

Not assessed

Assessor and date

Not assessed

Alternative assessments

Not assessed

Fill

The deployer's account

Entry details

Kind

Not assessed

Field

Healthcare (diabetes; obstetrics). Diabetes technology.

Purpose

Predictive low glucose suspend is built to stop insulin delivery when sensor glucose is predicted to fall low, to avoid hypoglycemia. The benefit was that purpose, with a successful pregnancy as the downstream outcome.

Dates

Date basis unassessed: 2021 (precision unassessed). Updated: 21 October 2026.

Stage

Not assessed

Version

SHA-256: bc612c5c94bf…

References

Other identifiers

Not assessed

Category mappings

Not assessed

Brief

Not assessed

Revisions

4 revisions. Latest: 21 October 2026.

Sources

  1. Case report Deployer

    Honoki H, Yagi K, Tsuda S, Wada T, Enkaku A, Nakagawa-Yokoyama M, Kamigishi M, Shikata M, Takikawa-Nishida A, Fujisaka S, Chujo D, Sasaoka T, Nakashima A, Saito S, Tobe K (2021). Type 1 diabetes woman with repeated miscarriages successfully gave birth after introducing an insulin pump with a predictive low glucose suspend feature. Diabetology International 12:324-329.

  2. Case report Deployer

    Honoki H et al. (2021). Diabetology International 12:324-329.

  3. Case report Deployer

    Zadáková E, Horová E (2025). Case Report: Hybrid closed-loop insulin pump can significantly improve awareness of hypoglycemia. Frontiers in Clinical Diabetes and Healthcare 6:1536038.