Maloney 2007.

Methods	Single‐centre, randomized controlled trial
Participants	Setting: US, paediatric ICU Inclusion criteria: intubated patients with intrinsic lung injury Exclusion criteria: mechanical ventilation through tracheostomy; after surgery/trauma; neuromuscular disease; upper airway disease; cyanotic heart failure Participant numbers: 34 randomly assigned; 3 withdrawn (2 from automated weaning group, 1 from standard care group); 31 analysed
Interventions	Automated weaning protocol (Java‐platform and Blaze Advisor rules described fully in the thesis) Standard weaning without a protocol at the discretion of physicians (detail not reported)
Outcomes	Weaning time (initiation of weaning [defined as 2 consecutive decreases in respiratory rate, pressure support, PEEP or tidal volume] to first extubation) Length of mechanical ventilation (Intubation to successful extubation) ICU and hospital length of stay Reintubation within 36 hours Number of blood gas and chest x‐ray orders Costs (total costs, PICU costs, ventilator‐associated costs)
Notes
Risk of bias
Bias	Authors' judgement	Support for judgement
Random sequence generation (selection bias)	Low risk	Computer‐generated randomization was provided in blocks of 10
Allocation concealment (selection bias)	Low risk	Computer‐generated randomization was provided
Blinding of participants and personnel (performance bias) All outcomes	Unclear risk	This was not reported
Blinding of outcome assessment (detection bias) All outcomes	Unclear risk	This was not reported
Incomplete outcome data (attrition bias) All outcomes	Low risk	Recruitment and attrition were reported
Selective reporting (reporting bias)	Low risk	No protocol was provided, but outcomes relevant to trials in this area are reported
Other bias	Low risk	None was apparent