xRead - Incorporating Artificial Intelligence into Clinical Practice (March 2026)

Ng et al. BMC Medical Informatics and Decision Making

(2025) 25:236

Page 9 of 24

Key Findings Novel Features

Study noted that indexing errors need improvement, especially those pertaining to word ambiguities and abbreviations;

recommend further refinement of the indexing tools used in ASR systems to mitigate these errors.

The authors recognize the limitations in handling non-English terms; suggest

developing ASR systems with multilingual capabilities, which could increase usability in diverse clinical settings​.

IBM via voice with medical vocabulary outperformed all other configurations using naturally speaking.

Index evaluation of Nomindex is com parable to previous evaluations. At

the current stage, the precision (73%) is too low to rely on this indexing but

the recall (90%) is high enough to use it as a machine-aided indexing tool.

AI Transcription

Proficiency (paper

specific outcomes)

Baseline (“at blank”) 8.23 3.59 2.34 6.02 0.36

5.67

Trained (“with learning”) 4.31* 2.67*

1.87*

7.14

0.54

4.21*

Baseline (“at blank”) 3.68 1.13 0.52 2.31 0.43

1.80

Trained (“with learning”) 2.16 1.22

0.66

1.19

0.00

1.71

Metric (F1 score, Precision 0.73

Precision, Recall, WER) Recall 0.90

“IBM via voice” SR tool: - Medical

Vocabulary - General

vocabulary

- Misspelling - Numbers

- Punctuation marks - Total

Gold standard “Naturally speak ing” SR tool: - Medical

Vocabulary - General

vocabulary

- Misspelling - Numbers

- Punctuation marks - Total

Comparator Type Subcategories Performance

Standard

Set of keywords manually ex

tracted from the

initial document.

Table 2 (continued)

Study Reference Happe et al., 2003 [10]