IMPORTANCE Accurate surgical scheduling affects patients, clinical staff, and use of physical resources. Although numerous retrospective analyses have suggested a potential for improvement, the real-world outcome of implementing a machine learning model to predict surgical case duration appears not to have been studied.
OBJECTIVESTo assess accuracy and real-world outcome from implementation of a machine learning model that predicts surgical case duration.
DESIGN, SETTING, AND PARTICIPANTSThis randomized clinical trial was conducted on 2 surgical campuses of a cancer specialty center. Patients undergoing colorectal and gynecology surgery at Memorial Sloan Kettering Cancer Center who were scheduled more than 1 day before surgery between April 7, 2018, and June 25, 2018, were included. The randomization process included 29 strata (11 gynecological surgeons at 2 campuses and 7 colorectal surgeons at a single campus) to ensure equal chance of selection for each surgeon and each campus. Patients undergoing more than 1 surgery during the study's timeframe were enrolled only once. Data analyses took place from July 2018 to November 2018.
INTERVENTIONSCases were assigned to machine learning-assisted surgical predictions 1 day before surgery and compared with a control group.
MAIN OUTCOMES AND MEASURESThe primary outcome measure was accurate prediction of the duration of each scheduled surgery, measured by (arithmetic) mean (SD) error and mean absolute error. Effects on patients and systems were measured by start time delay of following cases, the time between cases, and the time patients spent in presurgical area.RESULTS A total of 683 patients were included (mean [SD] age, 55.8 [13.8] years; 566 women [82.9%]); 72 were excluded. Of the 683 patients included, those assigned to the machine learning algorithm had significantly lower mean (SD) absolute error (control group, 59.3 [72] minutes; intervention group, 49.5 [66] minutes; difference, −9.8 minutes; P = .03) compared with the control group. Mean start-time delay for following cases (patient wait time in a presurgical area), dropped significantly: 62.4 minutes (from 70.2 minutes to 7.8 minutes) and 16.7 minutes (from 36.9 minutes to 20.2 minutes) for patients receiving colorectal and gynecology surgery, respectively. The overall mean (SD) reduction of wait time was 33.1 minutes per patient (from 49.4 minutes to 16.3 minutes per patient). Improved accuracy did not adversely inflate time between cases (surgeon wait time). There was marginal improvement (1.5 minutes, from a mean of 70.6 to 69.1 minutes) in time between the end of cases and start of to-follow cases using the predictive model, compared with the control group. Patients spent a mean of 25.2 fewer minutes in the facility before surgery (173.3 minutes vs 148.1 minutes), indicating a potential benefit vis-à-vis available resources for other patients before and after surgery.CONCLUSIONS AND RELEVANCE Implementing machine learning-generated predictions for surgical case durations may improve case duration accura...
Objectives
In the Fluid and Catheter Treatment Trial (FACTT) of the National
Institutes of Health Acute Respiratory Distress Syndrome Network, a
conservative fluid protocol (FACTT Conservative) resulted in a lower
cumulative fluid balance and better outcomes than a liberal fluid protocol
(FACTT Liberal). Subsequent Acute Respiratory Distress Syndrome Network
studies used a simplified conservative fluid protocol (FACTT Lite). The
objective of this study was to compare the performance of FACTT Lite, FACTT
Conservative, and FACTT Liberal protocols.
Design
Retrospective comparison of FACTT Lite, FACTT Conservative, and FACTT
Liberal. Primary outcome was cumulative fluid balance over 7 days. Secondary
outcomes were 60-day adjusted mortality and ventilator-free days through day
28. Safety outcomes were prevalence of acute kidney injury and new
shock.
Setting
ICUs of Acute Respiratory Distress Syndrome Network participating
hospitals.
Patients
Five hundred three subjects managed with FACTT Conservative, 497
subjects managed with FACTT Liberal, and 1,124 subjects managed with FACTT
Lite.
Interventions
Fluid management by protocol.
Measurements and Main Results
Cumulative fluid balance was 1,918 ± 323 mL in FACTT Lite,
−136 ±491 mL in FACTT Conservative, and 6,992 ± 502
mL in FACTT Liberal (p < 0.001). Mortality was not
different between groups (24% in FACTT Lite, 25% in FACTT
Conservative and Liberal, p = 0.84).
Ventilator-free days in FACTT Lite (14.9 ±0.3) were equivalent to
FACTT Conservative (14.6±0.5) (p = 0.61)
and greater than in FACTT Liberal (12.1 ±0.5, p
< 0.001 vs Lite). Acute kidney injury prevalence was 58% in
FACTT Lite and 57% in FACTT Conservative (p
= 0.72). Prevalence of new shock in FACTT Lite (9%) was
lower than in FACTT Conservative (13%) (p =
0.007 vs Lite) and similar to FACTT Liberal (11%)
(p = 0.18 vs Lite).
Conclusions
FACTT Lite had a greater cumulative fluid balance than FACTT
Conservative but had equivalent clinical and safety outcomes. FACTT Lite is
an alternative to FACTT Conservative for fluid management in Acute
Respiratory Distress Syndrome.
Several isoforms of neuronal nitric oxide synthase (nNOS) have been identified. Antisense approaches have been developed which can selectively down-regulate nNOS-1, which corresponds to the full-length nNOS originally cloned from the brain, and nNOS-2, a truncated form lacking two exons which is generated by alternative splicing, as demonstrated by decreases in mRNA levels. Antisense treatment also lowers nNOS enzymatic activity. Downregulation of nNOS-1 prevents the development of morphine tolerance. Whereas morphine analgesia is lost in control and mismatch-treated mice given daily morphine injections for 5 days, mice treated with antisense probes targeting nNOS-1 show no decrease in their morphine sensitivity over the same time period. Conversely, an antisense probe selectively targeting nNOS-2 blocks morphine analgesia, shifting the morphine dose-response curve over 2-fold to the right. Both systems are active at the spinal and the supraspinal levels. An antisense targeting inducible NOS is inactive. Studies with N G -nitro-L-arginine, which does not distinguish among NOS isoforms, indicate that the facilitating nNOS-2 system predominates at the spinal level while the inhibitory nNOS-1 system is the major supraspinal nNOS system. Thus, antisense mapping distinguishes at the functional level two isoforms of nNOS with opposing actions on morphine actions. The ability to selectively down-regulate splice variants opens many areas in the study of nNOS and other proteins.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.