Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients

Wojtusiak, Janusz; Asadzadehzanjani, Negin; Levy, Cari; Alemi, Farrokh; Williams, Allison E.

doi:10.1186/s12911-020-01368-8

BMC Medical Informatics and Decision Making

Table 6 Comparison of temporal and binary diagnosis coding as part of CBIT construction and evaluation

From: Computational Barthel Index: an automated tool for assessing and predicting activities of daily living among nursing home patients

AUC	Current assessment				3 month prediction				6 month prediction				12 month prediction
AUC	RF	LR	DT	NB	RF	LR	DT	NB	RF	LR	DT	NB	RF	LR	DT	NB
M_RE^d_τ
Temporal 4_9	0.95^*	0.85^*+	0.92⁺	0.87^*+	0.88	0.79^*+	0.83⁺	0.83⁺	0.81	0.77^*+	0.74⁺	0.78⁺	0.77	0.74^*+	0.70⁺	0.74⁺
Temporal 5_9	0.95	0.78^*+	0.92⁺	0.89⁺	0.88	0.76^*+	0.83⁺	0.83⁺	0.81	0.74⁺	0.74^*+	0.78⁺	0.77	0.71^*+	0.70⁺	0.74⁺
Temporal 6_9	0.95	0.78⁺	0.92⁺	0.90⁺	0.88	0.75⁺	0.83⁺	0.83⁺	0.81	0.74⁺	0.74⁺	0.78⁺	0.77	0.72⁺	0.70⁺	0.74⁺
Binary	0.94^*	0.94^*	0.91^*+	0.87^*+	0.87^*	0.87^*+	0.82^*+	0.80⁺	0.81	0.81^*+	0.74⁺	0.77^*+	0.77	0.77^*+	0.70⁺	0.74^*+
MS_RE^d_τ
Temporal 4_9	0.95	0.94^*+	0.92⁺	0.89⁺	0.88	0.88^*+	0.83⁺	0.82⁺	0.81^*	0.81^*+	0.74⁺	0.76⁺	0.77	0.77^*	0.70⁺	0.72⁺
Temporal 5_9	0.95	0.93^*+	0.92⁺	0.89⁺	0.88	0.84^*+	0.82⁺	0.82⁺	0.81^*	0.79^*+	0.74⁺	0.76⁺	0.77	0.75^*+	0.70⁺	0.72⁺
Temporal 6_9	0.95	0.76⁺	0.92⁺	0.90⁺	0.88	0.72⁺	0.83⁺	0.82⁺	0.81	0.71⁺	0.74⁺	0.76⁺	0.77	0.69⁺	0.70⁺	0.72⁺
Binary	0.94^*	0.94^*+	0.90^*+	0.90⁺	0.88^*	0.87^*+	0.81^*+	0.83⁺	0.81^*	0.81^*+	0.74^*+	0.78^*+	0.77	0.77^*	0.69⁺	0.74^*+
M_E^d_τ
Temporal 4_9	0.79	0.79^*+	0.72^*+	0.73⁺	0.76	0.76^*	0.68⁺	0.68⁺	0.75^*	0.75^*	0.66⁺	0.71⁺	0.73	0.72^*	0.64⁺	0.69⁺
Temporal 5_9	0.79	0.78^*+	0.71⁺	0.73⁺	0.76	0.75⁺	0.68⁺	0.68⁺	0.75	0.74^*+	0.66⁺	0.71⁺	0.73	0.71^*+	0.64⁺	0.69⁺
Temporal 6_9	0.79	0.78^*	0.72⁺	0.73⁺	0.76	0.75⁺	0.68⁺	0.68⁺	0.75	0.74	0.66⁺	0.71⁺	0.73	0.72⁺	0.64⁺	0.69⁺
Binary	0.78^*	0.78^*	0.70^*+	0.73⁺	0.76	0.76^*	0.67^*+	0.70^*+	0.75	0.75^*	0.66⁺	0.71^*+	0.72^*	0.73^*+	0.64⁺	0.69^*+
MS_E^d_τ
Temporal 4_9	0.79	0.77^*+	0.71⁺	0.64⁺	0.76	0.75^*₊	0.68⁺	0.63⁺	0.74	0.73^*+	0.66⁺	0.60⁺	0.72	0.72^*	0.63⁺	0.58⁺
Temporal 5_9	0.79	0.76^*+	0.71⁺	0.64⁺	0.76	0.73^*+	0.68⁺	0.63⁺	0.74	0.72^*+	0.66⁺	0.60⁺	0.72	0.71^*+	0.63⁺	0.58⁺
Temporal 6_9	0.79	0.75⁺	0.71⁺	0.64⁺	0.76	0.72⁺	0.68⁺	0.63⁺	0.74	0.71⁺	0.66⁺	0.60⁺	0.72	0.69⁺	0.63⁺	0.58⁺
Binary	0.76^*	0.77^*+	0.68^*+	0.74^*+	0.74^*	0.74^*	0.65^*+	0.71^*+	0.73^*	0.73^*	0.64^*+	0.71^*+	0.71^*	0.72^*+	0.63⁺	0.69^*+

The results are presented in terms of AUC for the current assessment and prediction up to 12 months ahead. Full models that include 578 attributes and simplified models with 50 attributes are shown. 4_9, 5_9, and 6_9 indicate the encoding of diagnoses not present in patient’s history for ± 9999, ± 99,999, and ± 999,999, respectively. *Indicates significance (p < 0.05) of coding systems compared to “6_9” and + indicates significance (p < 0.05) of different algorithms compared to random forest

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com