Propensity score analysis has been widely used in observational studies to make a causal inference. This study introduces three assumptions for causal inferences—conditional exchangeability, positivity, and consistency—and five steps for propensity score (PS) analysis—1) construct appropriate PS models, 2) check overlap in PS, 3) apply appropriate weighting (inverse probability of treatment weighting, standardized mortality ratio weighting, matching weights, and overlap weights) or matching methods according to the target of inference, 4) check the balance of covariates, and 5) estimate the effect of exposure appropriately. Finally, the advantages of PS analyses over conventional multivariable regression are discussed.

BACKGROUND

We aimed to develop and externally validate a novel machine learning model that can classify CT image findings as positive or negative for SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR).

METHODS

We used 2,928 images from a wide variety of case-control type data sources for the development and internal validation of the machine learning model. A total of 633 COVID-19 cases and 2,295 non-COVID-19 cases were included in the study. We randomly divided cases into training and tuning sets at a ratio of 8:2. For external validation, we used 893 images from 740 consecutive patients at 11 acute care hospitals suspected of having COVID-19 at the time of diagnosis. The dataset included 343 COVID-19 patients. The reference standard was RT-PCR.

RESULTS

In external validation, the sensitivity and specificity of the model were 0.869 and 0.432, at the low-level cutoff, 0.724 and 0.721, at the high-level cutoff. Area under the receiver operating characteristic was 0.76.

CONCLUSIONS

Our machine learning model exhibited a high sensitivity in external validation datasets and may assist physicians to rule out COVID-19 diagnosis in a timely manner at emergency departments. Further studies are warranted to improve model specificity.

BACKGROUND

Maoto is a Japanese Kampo formula used for treating febrile illnesses. However, researchers have not yet clarified its effect in preventing severe influenza among older adults. We evaluated the association between the addition of maoto to a neuraminidase inhibitor in older adults and reduced hospitalization following influenza.

METHODS

Using a prefecture-wide health insurance claims database, we identified outpatients aged ≥60 years who were diagnosed with influenza between September 2012 and August 2017. We performed one-to-one propensity score matching between patients who received maoto in addition to a neuraminidase inhibitor and those who received a neuraminidase inhibitor alone. Hospitalization within 7 days of influenza diagnosis was compared using the McNemar’s test. We performed subgroup analyses based on sex, age, and other characteristics.

RESULTS

We identified 57,366 eligible patients with influenza. Maoto was used in 8.1% of these patients. In 4,630 matched pairs, the 7-day hospitalization rate was 1.77% (n = 82) and 1.62% (n = 75) for patients with and without maoto, respectively; the difference between the groups was insignificant (P = 0.569). Subgroup analysis showed a tendency toward more hospitalizations within 7 days among patients aged 90 years or older who were prescribed maoto than those who were not (9.7% vs. 6.6%, P = 0.257).

CONCLUSIONS

Maoto use was not associated with decreased hospitalization rates in older adults with influenza. This warrants further research to evaluate the safety and effectiveness of maoto in different patient groups, particularly the oldest-old population.