Differences

This shows you the differences between two versions of the page.

--- workflow_dataset_to_rkns [2025/10/20 14:03] – old revision restored (2025/10/20 12:50) fabricio
+++ workflow_dataset_to_rkns [2025/10/20 14:03] (current) – [AI-Assisted Mapping Generation] fabricio
@@ Line 152: / Line 152: @@
 <code>
-I will provide you a list of EEG channels extracted from the original EDFs.
+I will provide you a list of physiological signal channels (e.g., EEG, EOG, EMG, respiratory, cardiac) extracted from original EDF files.
-I require an output in JSON format that maps channel names to new standardized names using grep-style regex replacements.
+I require an output in JSON format that maps each raw channel name to a standardized name using **sequential, grep-style regex replacements**.
-For example, this is a reference mapping. Note that replacements are applied in sequential order:
+Key requirements:
-```
+. **Include early normalization rules** to handle common delimiters (e.g., `_`, spaces, `.`, `/`, parentheses) by converting them to hyphens (`-`), collapsing multiple hyphens, and trimming leading/trailing hyphens.
+. All patterns must be **case-insensitive** (use `(?i)`).
+. Use **physiologically meaningful, NSRR/AASM-aligned names**, such as:
+   - `EEG-C3-M2` (not `EEG-C3_A2` or ambiguous forms)
+   - `EMG-LLEG` / `EMG-RLEG` for leg EMG (not `LAT`/`RAT` as position)
+   - `RESP-AIRFLOW-THERM` or `RESP-AIRFLOW-PRES` (not generic `RESP-NASAL`)
+   - `EOG-LOC` / `EOG-ROC` for eye channels
+   - `EMG-CHIN` for chin EMG
+   - `PULSE` for heart rate or pulse signals (unless raw ECG → `ECG`)
+. **Do not include a final catch-all rule** (e.g., `^(.+)$ → MISC-\1`) unless explicitly requested—most channels in the input list should be known and mapped specifically.
+. Replacements are applied **in order**, with each rule operating on the result of the previous one.
+Example reference snippet:
+```json
 {
-  "(?i)^ABDO\\sRES\\s*$": "RESP-ABD",
+  "(?i)[\\s_\\./\\(\\),]+": "-",
-  "(?i)^THOR\\sRES\\s*$": "RESP-CHEST",
+  "-+": "-",
-  "(?i)^EEG\\(sec\\)\\s*$": "EEG-C3-A2",
+  "^-|-$": "",
-  "_": "-"
+  "(?i)^abdomen$": "RESP-ABD",
+  "(?i)^c3_m2$": "EEG-C3-M2",
+  "(?i)^lat$": "EMG-LLEG"
 }
 ```
-The keys are regex patterns (case-insensitive), and the values are replacement strings. Groups in the pattern can be referenced in the replacement (e.g., ''\1'').
+Now, generate a similar JSON mapping for the following list of channel names:
-Based on the above example, generate a similar JSON mapping for the following list of channel names:
 ```
 [INSERT YOUR UNIQUE CHANNEL LIST HERE]
 ```
-Provide the output within a JSON code block.
+Provide the output **within a JSON code block only**—no explanations.
 </code>
 ===== Event Descriptions → assets/event_description_mapping.json =====