Evaluation of the clinical effect of an artificial intelligence-assisted diagnosis and treatment system for neonatal seizures in the real world: a multicenter clinical study protocol. / æ–°ç”Ÿå„¿æƒŠåŽ¥æ™ºèƒ½è¯Šç–—ç³»ç»ŸçœŸå®žåœºæ™¯ä¸´åºŠå®žæ–½æ•ˆæžœç»¼åˆè¯„ä»·çš„å¤šä¸­å¿ƒä¸´åºŠç ”ç©¶æ–¹æ¡ˆ.

Neonatal seizures are the most common clinical manifestations of critically ill neonates and often suggest serious diseases and complicated etiologies. The precise diagnosis of this disease can optimize the use of anti-seizure medication, reduce hospital costs, and improve the long-term neurodevelopmental outcomes. Currently, a few artificial intelligence-assisted diagnosis and treatment systems have been developed for neonatal seizures, but there is still a lack of high-level evidence for the diagnosis and treatment value in the real world. Based on an artificial intelligence-assisted diagnosis and treatment systems that has been developed for neonatal seizures, this study plans to recruit 370 neonates at a high risk of seizures from 6 neonatal intensive care units (NICUs) in China, in order to evaluate the effect of the system on the diagnosis, treatment, and prognosis of neonatal seizures in neonates with different gestational ages in the NICU. In this study, a diagnostic study protocol is used to evaluate the diagnostic value of the system, and a randomized parallel-controlled trial is designed to evaluate the effect of the system on the treatment and prognosis of neonates at a high risk of seizures. This multicenter prospective study will provide high-level evidence for the clinical application of artificial intelligence-assisted diagnosis and treatment systems for neonatal seizures in the real world.

[Amplitude integrated electroencephalography characteristics of normal preterm newborns: a multicenter clinical study].

OBJECTIVE: To study the characteristics of amplitude integrated electroencephalography (aEEG) in preterm infants and changes of maturation with gestational age. METHODS: aEEG monitoring was done within 3 days of age with domestically produced digital aEEG set (CFM3000). Duration of each recording was at least 4 hours. The continuity, sleep-wake cycle, voltage and bandwidth of all aEEG tracing were analyzed. RESULTS: The percent of continuity background increased from 30% of 28 weeks to 85.7% of 36 weeks (χ(2) = 28.2, P = 0.026); the percent of mature sleep-wake cycle increased from 10% of 28 weeks to 100% of 36 weeks (χ(2) = 192.4, P < 0.01). Low bound voltage increased with gestational age, from (6.8 ± 1.7) µV (28 w) to 9.7 - 10.1 µV (35 - 36 w) (F = 11.4, P < 0.01). Bandwidth of the narrow band decreases gradually with gestational age, from 1.45 cm (28 w) to (0.86 ± 0.24) cm (36 w) (F = 8.731, P < 0.01). The correlation coefficient for continuity, sleep-wake cycle, low bound voltage and bandwidth of narrow band, and total scores were 0.32, 0.81, 0.38, 0.55 and 0.78 respectively (P < 0.05). CONCLUSION: The older the gestational age of infants at birth, the more mature the aEEG pattern, manifested as increased continuity and sleep-wake cycle, the higher low bound voltage and more narrowed bandwidth with increased gestational age.

Effects of inhaled nitric oxide in neonatal hypoxemic respiratory failure from a multicenter controlled trial.

BACKGROUND: Hypoxemic respiratory failure (HRF) is one of the most common causes for neonatal infants requiring aggressive respiratory support. Inhaled nitric oxide (iNO) has been established routinely as an adjunct to conventional respiratory support in developed countries. The aim of this study was to investigate effects of iNO in neonates with HRF in resource limited condition with no or limited use of surfactant, high frequency oscillatory ventilation (HFOV) and extracorporeal membrane oxygenation. METHODS: A non-randomized, open, controlled study of efficacy of iNO was conducted over 18 months. Eligible term and near-term neonates from 28 hospitals with HRF (oxygenation index > 15) were enrolled prospectively into two groups as either iNO or control. Oxygenation improvement and mortality as primary endpoint were determined in relation with dosing and timing of iNO, severity of underlying diseases, complications and burden. Intention-to-treat principle was adopted for outcome assessment. Response to iNO at 10 or 20 parts per million (ppm) was determined by oxygenation in reference to the control (between-group) and the baseline (within-group). RESULTS: Compared to 93 controls, initial dose of iNO at 10 ppm in 107 treated infants significantly improved oxygenation from first hour (P = 0.046), with more partial- and non-responders improved oxygenation with subsequent 20 ppm NO (P = 0.018). This effect persisted on days 1 and 3, and resulted in relatively lower mortalities (11.2% vs. 15%) whereas fewer were treated with surfactant (10% vs. 27%), HFOV (< 5%) or postnatal corticosteroids (< 10%) in both groups. The overall outcomes at 28 days of postnatal life in the iNO-treated was not related to perinatal asphyxia, underlying diseases, severity of hypoxemia, or complications, but to the early use of iNO. The cost of hospital stay was not significantly different in both groups. CONCLUSIONS: With relatively limited use of surfactant and/or HFOV in neonatal HRF, significantly more responders were found in the iNO-treated patients as reflected by improved oxygenation in the first three days over the baseline level. It warrants a randomized, controlled trial for assessment of appropriate timing and long-term outcome of iNO.

Selective head cooling with mild systemic hypothermia after neonatal hypoxic-ischemic encephalopathy: a multicenter randomized controlled trial in China.

OBJECTIVE: To investigate the efficacy and safety of selective head cooling with mild systemic hypothermia in hypoxic-ischemic encephalopathy (HIE) in newborn infants. STUDY DESIGN: Infants with HIE were randomly assigned to the selective head cooling or control group. Selective head cooling was initiated within 6 hours after birth to a nasopharyngeal temperature of 34 degrees+/-0.2 degrees C and rectal temperature of 34.5 degrees to 35.0 degrees C for 72 hours. Rectal temperature was maintained at 36.0 degrees to 37.5 degrees C in the control group. Neurodevelopmental outcome was assessed at 18 months of age. The primary outcome was a combined end point of death and severe disability. RESULTS: One hundred ninety-four infants were available for analysis (100 and 94 infants in the selective head cooling and control group, respectively). For the selective head cooling and control groups, respectively, the combined outcome of death and severe disability was 31% and 49% (OR: 0.47; 95% CI: 0.26-0.84; P=.01), the mortality rate was 20% and 29% (OR:0.62; 95% CI: 0.32-1.20; P=.16), and the severe disability rate was 14% (11/80) and 28% (19/67) (OR: 0.40; 95% CI: 0.17-0.92; P=.01). CONCLUSIONS: Selective head cooling combined with mild systemic hypothermia for 72 hours may significantly decrease the combined outcome of severe disability and death, as well as severe disability.

The epidemiology of acute respiratory distress syndrome in pediatric intensive care units in China.

OBJECTIVE: To assess the incidence of, predisposing factors for, and the rates and relative risks of mortality from acute respiratory distress syndrome (ARDS) in pediatric patients. DESIGN: A prospective study in 12 consecutive months from 2004 to 2005 in 25 pediatric intensive care units (PICUs). PATIENTS AND SETTING: ARDS was diagnosed according to the 1994 American-European Consensus Conference definitions, applied to all severely ill admissions between 1 month and 14 years of age. The PICUs were in major municipalities and provincial cities, and half were university affiliated. MEASUREMENTS AND RESULTS: From a total of 12,018 admissions, 7,269 were severely ill. One hundred and five (1.44%) patients developed ARDS and 64 (61.0%) died, which accounts for 13.2%, of the total ICU death (n = 485, 6.7%) or a nine times relative risk of dying. The median age at onset of ARDS was 24 months and 40% were less than 12 month old. Median time from PICU admission to the onset of ARDS was 16 h, and in 63% <24 h. Pneumonia (55.2%) and sepsis (22.9%) were the major predisposing factors for ARDS. These were respectively 14 and 5 times as high a death rate as those of the severely ill patients without ARDS. CONCLUSIONS: ARDS has a high mortality in these Chinese PICUs, especially in those with pneumonia and sepsis, and adequate management including lung protective ventilation strategy is required.